Tootfinder

SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
Mustafa Shukor, Dana Aubakirova, Francesco Capuano, Pepijn Kooijmans, Steven Palma, Adil Zouitine, Michel Aractingi, Caroline Pascal, Martino Russi, Andres Marafioti, Simon Alibert, Matthieu Cord, Thomas Wolf, Remi Cadene
https://arxiv.org/abs/2506.018…

SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
Vision-language models (VLMs) pretrained on large-scale multimodal datasets encode rich visual and linguistic knowledge, making them a strong foundation for robotics. Rather than training robotic policies from scratch, recent approaches adapt VLMs into vision-language-action (VLA) models that enable natural language-driven perception and control. However, existing VLAs are typically massive--often with billions of parameters--leading to high training costs and limited real-world deployability. …

Adapting Language Models to Indonesian Local Languages: An Empirical Study of Language Transferability on Zero-Shot Settings
Rifki Afina Putri
https://arxiv.org/abs/2507.01645

Adapting Language Models to Indonesian Local Languages: An Empirical Study of Language Transferability on Zero-Shot Settings
In this paper, we investigate the transferability of pre-trained language models to low-resource Indonesian local languages through the task of sentiment analysis. We evaluate both zero-shot performance and adapter-based transfer on ten local languages using models of different types: a monolingual Indonesian BERT, multilingual models such as mBERT and XLM-R, and a modular adapter-based approach called MAD-X. To better understand model behavior, we group the target languages into three categori…

Language-Guided Long Horizon Manipulation with LLM-based Planning and Visual Perception
Changshi Zhou, Haichuan Xu, Ningquan Gu, Zhipeng Wang, Bin Cheng, Pengpeng Zhang, Yanchao Dong, Mitsuhiro Hayashibe, Yanmin Zhou, Bin He
https://arxiv.org/abs/2509.02324

Language-Guided Long Horizon Manipulation with LLM-based Planning and Visual Perception
Language-guided long-horizon manipulation of deformable objects presents significant challenges due to high degrees of freedom, complex dynamics, and the need for accurate vision-language grounding. In this work, we focus on multi-step cloth folding, a representative deformable-object manipulation task that requires both structured long-horizon planning and fine-grained visual perception. To this end, we propose a unified framework that integrates a Large Language Model (LLM)-based planner, a V…

YouTube... started defaulting to auto-translated audio.
It would default to my "preferred language".
My #preference is the original #language, and I speak multiple ones. That is not an option though. So I have to manually change the audio track or turn off CC all the time - w…

A Survey: Towards Privacy and Security in Mobile Large Language Models
Honghui Xu, Kaiyang Li, Wei Chen, Danyang Zheng, Zhiyuan Li, Zhipeng Cai
https://arxiv.org/abs/2509.02411 …

A Survey: Towards Privacy and Security in Mobile Large Language Models
Mobile Large Language Models (LLMs) are revolutionizing diverse fields such as healthcare, finance, and education with their ability to perform advanced natural language processing tasks on-the-go. However, the deployment of these models in mobile and edge environments introduces significant challenges related to privacy and security due to their resource-intensive nature and the sensitivity of the data they process. This survey provides a comprehensive overview of privacy and security issues a…

Go is 80/20 language: https://blog.kowalczyk.info/article/d-2025-06-26/go-is-8020-language.html
Good piece, a bit misleading on a couple of Go details but essentially right I think. I spent my last 20 years of employment working in Java-heavy …

This https://arxiv.org/abs/2505.14690 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csPL_…

SGL: A Structured Graphics Language
This paper introduces SGL, a graphics language that is aesthetically similar to SQL. SGL is based on traditional grammars of graphics, as well as Vega-Lite's composition algebra. SGL demonstrates that the grammatical approach to graphics lends itself naturally to a SQL-like language. As a graphical counterpart to SQL, SGL facilitates the addition of visualization capabilities to SQL query interfaces. This paper presents components of the SGL language alongside examples. Comparisons to SQL and e…

Dredging up recollections of my experience as R6RS editor for my PLSS talk tomorrow.
https://2025.ecoop.org/details/plss-2025-papers/8/Do-Programming-Languages-Fulfill-Requirements-Should-They-

Ensemble Debates with Local Large Language Models for AI Alignment
Ephraiem Sarabamoun
https://arxiv.org/abs/2509.00091 https://arxiv.org/pdf/2509.00091

Ensemble Debates with Local Large Language Models for AI Alignment
As large language models (LLMs) take on greater roles in high-stakes decisions, alignment with human values is essential. Reliance on proprietary APIs limits reproducibility and broad participation. We study whether local open-source ensemble debates can improve alignmentoriented reasoning. Across 150 debates spanning 15 scenarios and five ensemble configurations, ensembles outperform single-model baselines on a 7-point rubric (overall: 3.48 vs. 3.13), with the largest gains in reasoning depth …

GLoSS: Generative Language Models with Semantic Search for Sequential Recommendation
Krishna Acharya, Aleksandr V. Petrov, Juba Ziani
https://arxiv.org/abs/2506.01910

GLoSS: Generative Language Models with Semantic Search for Sequential Recommendation
We propose Generative Low-rank language model with Semantic Search (GLoSS), a generative recommendation framework that combines large language models with dense retrieval for sequential recommendation. Unlike prior methods such as GPT4Rec, which rely on lexical matching via BM25, GLoSS uses semantic search to retrieve relevant items beyond lexical matching. For query generation, we employ 4-bit quantized LlaMA-3 models fine-tuned with low-rank adaptation (LoRA), enabling efficient training and …

Enhancing Finite State Machine Design Automation with Large Language Models and Prompt Engineering Techniques
Qun-Kai Lin, Cheng Hsu, Tian-Sheuan Chang
https://arxiv.org/abs/2506.00001

Enhancing Finite State Machine Design Automation with Large Language Models and Prompt Engineering Techniques
Large Language Models (LLMs) have attracted considerable attention in recent years due to their remarkable compatibility with Hardware Description Language (HDL) design. In this paper, we examine the performance of three major LLMs, Claude 3 Opus, ChatGPT-4, and ChatGPT-4o, in designing finite state machines (FSMs). By utilizing the instructional content provided by HDLBits, we evaluate the stability, limitations, and potential approaches for improving the success rates of these models. Further…

CODEMENV: Benchmarking Large Language Models on Code Migration
Keyuan Cheng, Xudong Shen, Yihao Yang, Tengyue Wang, Yang Cao, Muhammad Asif Ali, Hanbin Wang, Lijie Hu, Di Wang
https://arxiv.org/abs/2506.00894

CODEMENV: Benchmarking Large Language Models on Code Migration
Large language models (LLMs) have shown remarkable capabilities across various software engineering tasks; however, their effectiveness in code migration, adapting code to run in different environments, remains insufficiently studied. In this work, we introduce CODEMENV: Code Migration Across Environment, a new benchmark specifically designed to assess LLMs' abilities in code migration scenarios. CODEMENV consists of 922 examples spanning 19 Python and Java packages, and covers three core tasks…

⛓️‍💥 Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations
#ai #llm

Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations
Modern tokenizers employ deterministic algorithms to map text into a single "canonical" token sequence, yet the same string can be encoded as many non-canonical tokenizations using the tokenizer vocabulary. In this work, we investigate the robustness of LMs to text encoded with non-canonical tokenizations entirely unseen during training. Surprisingly, when evaluated across 20 benchmarks, we find that instruction-tuned models retain up to 93.4% of their original performance when given a randomly…

Dissecting Atomic Facts: Visual Analytics for Improving Fact Annotations in Language Model Evaluation
Manuel Schmidt, Daniel A. Keim, Frederik L. Dennig
https://arxiv.org/abs/2509.01460

Dissecting Atomic Facts: Visual Analytics for Improving Fact Annotations in Language Model Evaluation
Factuality evaluation of large language model (LLM) outputs requires decomposing text into discrete "atomic" facts. However, existing definitions of atomicity are underspecified, with empirical results showing high disagreement among annotators, both human and model-based, due to unresolved ambiguity in fact decomposition. We present a visual analytics concept to expose and analyze annotation inconsistencies in fact extraction. By visualizing semantic alignment, granularity and referential depe…

HCCM: Hierarchical Cross-Granularity Contrastive and Matching Learning for Natural Language-Guided Drones
Hao Ruan, Jinliang Lin, Yingxin Lai, Zhiming Luo, Shaozi Li
https://arxiv.org/abs/2508.21539

HCCM: Hierarchical Cross-Granularity Contrastive and Matching Learning for Natural Language-Guided Drones
Natural Language-Guided Drones (NLGD) provide a novel paradigm for tasks such as target matching and navigation. However, the wide field of view and complex compositional semantics in drone scenarios pose challenges for vision-language understanding. Mainstream Vision-Language Models (VLMs) emphasize global alignment while lacking fine-grained semantics, and existing hierarchical methods depend on precise entity partitioning and strict containment, limiting effectiveness in dynamic environments…

The World As Large Language Models See It: Exploring the reliability of LLMs in representing geographical features
Omid Reza Abbasi, Franz Welscher, Georg Weinberger, Johannes Scholz
https://arxiv.org/abs/2506.00203

The World As Large Language Models See It: Exploring the reliability of LLMs in representing geographical features
As large language models (LLMs) continue to evolve, questions about their trustworthiness in delivering factual information have become increasingly important. This concern also applies to their ability to accurately represent the geographic world. With recent advancements in this field, it is relevant to consider whether and to what extent LLMs' representations of the geographical world can be trusted. This study evaluates the performance of GPT-4o and Gemini 2.0 Flash in three key geospatial …

Towards Fundamental Language Models: Does Linguistic Competence Scale with Model Size?
Jaime Collado-Monta\~nez, L. Alfonso Ure\~na-L\'opez, Arturo Montejo-R\'aez
https://arxiv.org/abs/2509.02225

Towards Fundamental Language Models: Does Linguistic Competence Scale with Model Size?
Large Language Models offer impressive language capabilities but suffer from well-known limitations, including hallucinations, biases, privacy concerns, and high computational costs. These issues are largely driven by the combination of linguistic competence and factual memorization within a single monolithic model. This paper introduces and empirically supports the Fundamental Language Model (FLM) paradigm, which advocates for smaller, linguistically competent models that offload factual retri…

Big News! The completely #opensource #LLM #Apertus 🇨🇭 has been released today:
📰

Apertus: A fully open, transparent, multilingual language model
EPFL, ETH Zurich and the Swiss National Supercomputing Centre (CSCS) released Apertus today, Switzerland’s first large-scale, open, multilingual language model — a milestone in generative AI for transparency and diversity.

How large language models judge and influence human cooperation
Alexandre S. Pires, Laurens Samson, Sennay Ghebreab, Fernando P. Santos
https://arxiv.org/abs/2507.00088

How large language models judge and influence human cooperation
Humans increasingly rely on large language models (LLMs) to support decisions in social settings. Previous work suggests that such tools shape people's moral and political judgements. However, the long-term implications of LLM-based social decision-making remain unknown. How will human cooperation be affected when the assessment of social interactions relies on language models? This is a pressing question, as human cooperation is often driven by indirect reciprocity, reputations, and the capaci…

Beyond Pixel Agreement: Large Language Models as Clinical Guardrails for Reliable Medical Image Segmentation
Jiaxi Sheng, Leyi Yu, Haoyue Li, Yifan Gao, Xin Gao
https://arxiv.org/abs/2506.01841

Beyond Pixel Agreement: Large Language Models as Clinical Guardrails for Reliable Medical Image Segmentation
Evaluating AI-generated medical image segmentations for clinical acceptability poses a significant challenge, as traditional pixelagreement metrics often fail to capture true diagnostic utility. This paper introduces Hierarchical Clinical Reasoner (HCR), a novel framework that leverages Large Language Models (LLMs) as clinical guardrails for reliable, zero-shot quality assessment. HCR employs a structured, multistage prompting strategy that guides LLMs through a detailed reasoning process, enco…

A Survey on Vision-Language-Action Models: An Action Tokenization Perspective
Yifan Zhong, Fengshuo Bai, Shaofei Cai, Xuchuan Huang, Zhang Chen, Xiaowei Zhang, Yuanfei Wang, Shaoyang Guo, Tianrui Guan, Ka Nam Lui, Zhiquan Qi, Yitao Liang, Yuanpei Chen, Yaodong Yang
https://arxiv.org/abs/2507.01925

A Survey on Vision-Language-Action Models: An Action Tokenization Perspective
The remarkable advancements of vision and language foundation models in multimodal understanding, reasoning, and generation has sparked growing efforts to extend such intelligence to the physical world, fueling the flourishing of vision-language-action (VLA) models. Despite seemingly diverse approaches, we observe that current VLA models can be unified under a single framework: vision and language inputs are processed by a series of VLA modules, producing a chain of \textit{action tokens} that …

DIY-MKG: An LLM-Based Polyglot Language Learning System
Kenan Tang, Yanhong Li, Yao Qin
https://arxiv.org/abs/2507.01872 https://arxi…

DIY-MKG: An LLM-Based Polyglot Language Learning System
Existing language learning tools, even those powered by Large Language Models (LLMs), often lack support for polyglot learners to build linguistic connections across vocabularies in multiple languages, provide limited customization for individual learning paces or needs, and suffer from detrimental cognitive offloading. To address these limitations, we design Do-It-Yourself Multilingual Knowledge Graph (DIY-MKG), an open-source system that supports polyglot language learning. DIY-MKG allows the…

SHERPA: A Model-Driven Framework for Large Language Model Execution
Boqi Chen, Kua Chen, Jos\'e Antonio Hern\'andez L\'opez, Gunter Mussbacher, D\'aniel Varr\'o, Amir Feizpour
https://arxiv.org/abs/2509.00272

SHERPA: A Model-Driven Framework for Large Language Model Execution
Recently, large language models (LLMs) have achieved widespread application across various fields. Despite their impressive capabilities, LLMs suffer from a lack of structured reasoning ability, particularly for complex tasks requiring domain-specific best practices, which are often unavailable in the training data. Although multi-step prompting methods incorporating human best practices, such as chain-of-thought and tree-of-thought, have gained popularity, they lack a general mechanism to cont…

MLorc: Momentum Low-rank Compression for Large Language Model Adaptation
Wei Shen, Yaxiang Zhang, Minhui Huang, Mengfan Xu, Jiawei Zhang, Cong Shen
https://arxiv.org/abs/2506.01897

MLorc: Momentum Low-rank Compression for Large Language Model Adaptation
With increasing size of large language models (LLMs), full-parameter fine-tuning imposes substantial memory demands. To alleviate this, we propose a novel memory-efficient training paradigm called Momentum Low-rank compression (MLorc). By directly compressing and reconstructing momentum rather than gradients, MLorc avoids imposing a fixed-rank constraint on weight update matrices and better preserves the training dynamics of full-parameter fine-tuning, in contrast to existing low-rank approache…

ChopChop: a Programmable Framework for Semantically Constraining the Output of Language Models
Shaan Nagy, Timothy Zhou, Nadia Polikarpova, Loris D'Antoni
https://arxiv.org/abs/2509.00360

ChopChop: a Programmable Framework for Semantically Constraining the Output of Language Models
Language models (LMs) can generate code, but cannot guarantee its correctness--producing outputs that often violate type safety, program invariants, or semantic equivalence. Constrained decoding offers a solution by restricting generation to programs that satisfy desired properties. Yet, existing methods are limited to shallow syntactic constraints or rely on brittle, ad hoc encodings of semantics over token sequences. We present ChopChop, the first programmable framework for semantic constra…

PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancement
Xubin Yue, Zhenhua Xu, Wenpeng Xing, Jiahui Yu, Mohan Li, Meng Han
https://arxiv.org/abs/2509.00918

PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancement
Addressing the intellectual property protection challenges in commercial deployment of large language models (LLMs), existing black-box fingerprinting techniques face dual challenges from incremental fine-tuning erasure and feature-space defense due to their reliance on overfitting high-perplexity trigger patterns. Recent work has revealed that model editing in the fingerprinting domain offers distinct advantages, including significantly lower false positive rates, enhanced harmlessness, and su…

SysLLMatic: Large Language Models are Software System Optimizers
Huiyun Peng, Arjun Gupte, Ryan Hasler, Nicholas John Eliopoulos, Chien-Chou Ho, Rishi Mantri, Leo Deng, Konstantin L\"aufer, George K. Thiruvathukal, James C. Davis
https://arxiv.org/abs/2506.01249

SysLLMatic: Large Language Models are Software System Optimizers
Automatic software system optimization can improve software speed, reduce operating costs, and save energy. Traditional approaches to optimization rely on manual tuning and compiler heuristics, limiting their ability to generalize across diverse codebases and system contexts. Recent methods using Large Language Models (LLMs) offer automation to address these limitations, but often fail to scale to the complexity of real-world software systems and applications. We present SysLLMatic, a system th…

Teaching a Language Model to Speak the Language of Tools
Simeon Emanuilov
https://arxiv.org/abs/2506.23394 https://arxiv.org/pdf/2506…

Teaching a Language Model to Speak the Language of Tools
External tool integration through function-calling is essential for practical language model applications, yet most multilingual models lack reliable tool-use capabilities in non-English languages. Even state-of-the-art multilingual models struggle with determining when to use tools and generating the structured outputs required for function calls, often exhibiting language confusion when prompted in lower-resource languages. This work presents a methodology for adapting existing language model…

Hybrid EEG--Driven Brain--Computer Interface: A Large Language Model Framework for Personalized Language Rehabilitation
Ismail Hossain, Mridul Banik
https://arxiv.org/abs/2507.22892

Hybrid EEG--Driven Brain--Computer Interface: A Large Language Model Framework for Personalized Language Rehabilitation
Conventional augmentative and alternative communication (AAC) systems and language-learning platforms often fail to adapt in real time to the user's cognitive and linguistic needs, especially in neurological conditions such as post-stroke aphasia or amyotrophic lateral sclerosis. Recent advances in noninvasive electroencephalography (EEG)--based brain-computer interfaces (BCIs) and transformer--based large language models (LLMs) offer complementary strengths: BCIs capture users' neural intent w…

SafeCOMM: What about Safety Alignment in Fine-Tuned Telecom Large Language Models?
Aladin Djuhera, Swanand Ravindra Kadhe, Farhan Ahmed, Syed Zawad, Holger Boche, Walid Saad
https://arxiv.org/abs/2506.00062

SafeCOMM: What about Safety Alignment in Fine-Tuned Telecom Large Language Models?
Fine-tuning large language models (LLMs) for telecom tasks and datasets is a common practice to adapt general-purpose models to the telecom domain. However, little attention has been paid to how this process may compromise model safety. Recent research has shown that even benign fine-tuning can degrade the safety alignment of LLMs, causing them to respond to harmful or unethical user queries. In this paper, we investigate this issue for telecom-tuned LLMs using three representative datasets fea…

Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding
Tao Lin, Gen Li, Yilei Zhong, Yanwen Zou, Bo Zhao
https://arxiv.org/abs/2507.00416 …

Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding
Vision-Language-Action (VLA) models have emerged as a promising framework for enabling generalist robots capable of perceiving, reasoning, and acting in the real world. These models usually build upon pretrained Vision-Language Models (VLMs), which excel at semantic understanding due to large-scale text pretraining. However, VLMs typically lack precise spatial understanding capabilities, as they are primarily tuned on 2D image-text pairs without 3D supervision. To address this limitation, recen…

MultiStream-LLM: Bridging Modalities for Robust Sign Language Translation
Marshall Thomas, Edward Fish, Richard Bowden
https://arxiv.org/abs/2509.00030 https://

MultiStream-LLM: Bridging Modalities for Robust Sign Language Translation
Despite progress in gloss-free Sign Language Translation (SLT), monolithic end-to-end models consistently fail on two critical components of natural signing: the precise recognition of high-speed fingerspelling and the integration of asynchronous non-manual cues from the face. Recent progress in Automated Sign Language Translation with Large Language Models has side stepped this challenge, forcing a single network to learn these simultaneously resulting in poor performance when tasked with tran…

Counterfactual Sensitivity for Faithful Reasoning in Language Models
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
https://arxiv.org/abs/2509.01544 https://

Counterfactual Sensitivity for Faithful Reasoning in Language Models
Large language models (LLMs) often produce correct answers while relying on flawed or irrelevant reasoning traces, undermining their trustworthiness in high-stakes domains. We propose Counterfactual Sensitivity Regularization (CSR), a lightweight training objective that enforces dependence between intermediate reasoning and final outputs. CSR introduces automated, operator-level counterfactual interventions (e.g., swapping "+" with "-") during training and penalizes models that preserve the sam…

This https://arxiv.org/abs/2504.19583 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Graph-Based Spectral Decomposition for Parameter Coordination in Language Model Fine-Tuning
This paper proposes a parameter collaborative optimization algorithm for large language models, enhanced with graph spectral analysis. The goal is to improve both fine-tuning efficiency and structural awareness during training. In the proposed method, the parameters of a pre-trained language model are treated as nodes in a graph. A weighted graph is constructed, and Laplacian spectral decomposition is applied to enable frequency-domain modeling and structural representation of the parameter spa…

Globality and Regions
Hector Gramaglia
https://arxiv.org/abs/2507.01664 https://arxiv.org/pdf/2507.01664

Globality and Regions
We obtain a characterization of global variables by unifying abstraction with region abstraction in a region-based language. More precisely, in a previous work a language called global was presented, whose virtue is to provide a conceptually clear way of introducing imperative operations in a functional language. Memory safety is provided by the concept of linear protection, which connects the global system to a linear one. In this paper we show that the concept of global variable provided by t…

LLMHoney: A Real-Time SSH Honeypot with Large Language Model-Driven Dynamic Response Generation
Pranjay Malhotra
https://arxiv.org/abs/2509.01463 https://a…

LLMHoney: A Real-Time SSH Honeypot with Large Language Model-Driven Dynamic Response Generation
Cybersecurity honeypots are deception tools for engaging attackers and gather intelligence, but traditional low or medium-interaction honeypots often rely on static, pre-scripted interactions that can be easily identified by skilled adversaries. This Report presents LLMHoney, an SSH honeypot that leverages Large Language Models (LLMs) to generate realistic, dynamic command outputs in real time. LLMHoney integrates a dictionary-based virtual file system to handle common commands with low latency…

OG-VLA: 3D-Aware Vision Language Action Model via Orthographic Image Generation
Ishika Singh, Ankit Goyal, Stan Birchfield, Dieter Fox, Animesh Garg, Valts Blukis
https://arxiv.org/abs/2506.01196

OG-VLA: 3D-Aware Vision Language Action Model via Orthographic Image Generation
We introduce OG-VLA, a novel architecture and learning framework that combines the generalization strengths of Vision Language Action models (VLAs) with the robustness of 3D-aware policies. We address the challenge of mapping natural language instructions and multi-view RGBD observations to quasi-static robot actions. 3D-aware robot policies achieve state-of-the-art performance on precise robot manipulation tasks, but struggle with generalization to unseen instructions, scenes, and objects. On …

Applying Large Language Models to Issue Classification: Revisiting with Extended Data and New Models
Gabriel Aracena, Kyle Luster, Fabio Santos, Igor Steinmacher, Marco A. Gerosa
https://arxiv.org/abs/2506.00128

Applying Large Language Models to Issue Classification: Revisiting with Extended Data and New Models
Effective prioritization of issue reports in software engineering helps to optimize resource allocation and information recovery. However, manual issue classification is laborious and lacks scalability. As an alternative, many open source software (OSS) projects employ automated processes for this task, yet this method often relies on large datasets for adequate training. Traditionally, machine learning techniques have been used for issue classification. More recently, large language models (LL…

chDzDT: Word-level morphology-aware language model for Algerian social media text
Abdelkrime Aries
https://arxiv.org/abs/2509.01772 https://arxiv.org/pdf/2…

chDzDT: Word-level morphology-aware language model for Algerian social media text
Pre-trained language models (PLMs) have substantially advanced natural language processing by providing context-sensitive text representations. However, the Algerian dialect remains under-represented, with few dedicated models available. Processing this dialect is challenging due to its complex morphology, frequent code-switching, multiple scripts, and strong lexical influences from other languages. These characteristics complicate tokenization and reduce the effectiveness of conventional word-…

Large language models can learn and generalize steganographic chain-of-thought under process supervision
Joey Skaf, Luis Ibanez-Lissen, Robert McCarthy, Connor Watts, Vasil Georgiv, Hannes Whittingham, Lorena Gonzalez-Manzano, David Lindner, Cameron Tice, Edward James Young, Puria Radmard
https://arxiv.org/abs/2506.01926

Large language models can learn and generalize steganographic chain-of-thought under process supervision
Chain-of-thought (CoT) reasoning not only enhances large language model performance but also provides critical insights into decision-making processes, marking it as a useful tool for monitoring model intent and planning. By proactively preventing models from acting on CoT indicating misaligned or harmful intent, CoT monitoring can be used to reduce risks associated with deploying models. However, developers may be incentivized to train away the appearance of harmful intent from CoT traces, by …

Empowering Large Language Model for Sequential Recommendation via Multimodal Embeddings and Semantic IDs
Yuhao Wang, Junwei Pan, Xinhang Li, Maolin Wang, Yuan Wang, Yue Liu, Dapeng Liu, Jie Jiang, Xiangyu Zhao
https://arxiv.org/abs/2509.02017

Empowering Large Language Model for Sequential Recommendation via Multimodal Embeddings and Semantic IDs
Sequential recommendation (SR) aims to capture users' dynamic interests and sequential patterns based on their historical interactions. Recently, the powerful capabilities of large language models (LLMs) have driven their adoption in SR. However, we identify two critical challenges in existing LLM-based SR methods: 1) embedding collapse when incorporating pre-trained collaborative embeddings and 2) catastrophic forgetting of quantized embeddings when utilizing semantic IDs. These issues dampen …

This https://arxiv.org/abs/2505.19433 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression
Post-training compression reduces the computational and memory costs of large language models (LLMs), enabling resource-efficient deployment. However, existing compression benchmarks only focus on language modeling (e.g., perplexity) and natural language understanding tasks (e.g., GLUE accuracy), ignoring the agentic capabilities - workflow, tool use/function call, long-context understanding and real-world application. We introduce the Agent Compression Benchmark (ACBench), the first comprehens…

AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models
Aashray Reddy, Andrew Zagula, Nicholas Saban
https://arxiv.org/abs/2507.01020

AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models
Large Language Models (LLMs) continue to exhibit vulnerabilities to jailbreaking attacks: carefully crafted malicious inputs intended to circumvent safety guardrails and elicit harmful responses. As such, we present AutoAdv, a novel framework that automates adversarial prompt generation to systematically evaluate and expose vulnerabilities in LLM safety mechanisms. Our approach leverages a parametric attacker LLM to produce semantically disguised malicious prompts through strategic rewriting te…

Pitfalls of Evaluating Language Models with Open Benchmarks
Md. Najib Hasan (Wichita State University), Mohammad Fakhruddin Babar (Washington State University), Souvika Sarkar (Wichita State University), Monowar Hasan (Washington State University), Santu Karmaker (University of Central Florida)
https://arxiv.org/abs/2507.00460…

Pitfalls of Evaluating Language Models with Open Benchmarks
Open Large Language Model (LLM) benchmarks, such as HELM and BIG-bench, offer standardized, transparent protocols that facilitate the fair comparison, reproducibility, and iterative advancement of Language Models (LMs). However, their openness also introduces critical and underexplored pitfalls. This study exposes these weaknesses by systematically constructing ``cheating'' models -- smaller variants of BART, T5, and GPT-2 fine-tuned directly on public test sets -- which achieve top rankings on…

Language and Experience: A Computational Model of Social Learning in Complex Tasks
C\'edric Colas, Tracey Mills, Ben Prystawski, Michael Henry Tessler, Noah Goodman, Jacob Andreas, Joshua Tenenbaum
https://arxiv.org/abs/2509.00074

Language and Experience: A Computational Model of Social Learning in Complex Tasks
The ability to combine linguistic guidance from others with direct experience is central to human development, enabling safe and rapid learning in new environments. How do people integrate these two sources of knowledge, and how might AI systems? We present a computational framework that models social learning as joint probabilistic inference over structured, executable world models given sensorimotor and linguistic data. We make this possible by turning a pretrained language model into a proba…

Legal Compliance Evaluation of Smart Contracts Generated By Large Language Models
Chanuka Wijayakoon, Hai Dong, H. M. N. Dilum Bandara, Zahir Tari, Anurag Soin
https://arxiv.org/abs/2506.00943

Legal Compliance Evaluation of Smart Contracts Generated By Large Language Models
Smart contracts can implement and automate parts of legal contracts, but ensuring their legal compliance remains challenging. Existing approaches such as formal specification, verification, and model-based development require expertise in both legal and software development domains, as well as extensive manual effort. Given the recent advances of Large Language Models (LLMs) in code generation, we investigate their ability to generate legally compliant smart contracts directly from natural lang…

Upcycling Candidate Tokens of Large Language Models for Query Expansion
Jinseok Kim, Sukmin Cho, Soyeong Jeong, Sangyeop Kim, Sungzoon Cho
https://arxiv.org/abs/2509.02377 https…

Upcycling Candidate Tokens of Large Language Models for Query Expansion
Query Expansion (QE) improves retrieval performance by enriching queries with related terms. Recently, Large Language Models (LLMs) have been used for QE, but existing methods face a trade-off: generating diverse terms boosts performance but increases computational cost. To address this challenge, we propose Candidate Token Query Expansion (CTQE), which extracts diverse and relevant terms from a single LLM decoding pass by leveraging unselected candidate tokens. These tokens, though not part of…

Large Language Model-Driven Closed-Loop UAV Operation with Semantic Observations
Wenhao Wang, Yanyan Li, Long Jiao, Jiawei Yuan
https://arxiv.org/abs/2507.01930

Large Language Model-Driven Closed-Loop UAV Operation with Semantic Observations
Large Language Models (LLMs) have revolutionized robotic autonomy, including Unmanned Aerial Vehicles (UAVs). Recent studies have demonstrated the potential of LLMs for translating human instructions into executable control code for UAV operations. However, LLMs still face challenges from logical reasoning and complex decision-making, leading to concerns about the reliability of LLM-driven UAV operations. In this paper, we propose a LLM-driven closed-loop control framework that enables reliable…

Comparative Study of Pre-Trained BERT and Large Language Models for Code-Mixed Named Entity Recognition
Mayur Shirke, Amey Shembade, Pavan Thorat, Madhushri Wagh, Raviraj Joshi
https://arxiv.org/abs/2509.02514

Comparative Study of Pre-Trained BERT and Large Language Models for Code-Mixed Named Entity Recognition
Named Entity Recognition (NER) in code-mixed text, particularly Hindi-English (Hinglish), presents unique challenges due to informal structure, transliteration, and frequent language switching. This study conducts a comparative evaluation of code-mixed fine-tuned models and non-code-mixed multilingual models, along with zero-shot generative large language models (LLMs). Specifically, we evaluate HingBERT, HingMBERT, and HingRoBERTa (trained on code-mixed data), and BERT Base Cased, IndicBERT, R…

Enabling Transparent Cyber Threat Intelligence Combining Large Language Models and Domain Ontologies
Luca Cotti, Anisa Rula, Devis Bianchini, Federico Cerutti
https://arxiv.org/abs/2509.00081

Enabling Transparent Cyber Threat Intelligence Combining Large Language Models and Domain Ontologies
Effective Cyber Threat Intelligence (CTI) relies upon accurately structured and semantically enriched information extracted from cybersecurity system logs. However, current methodologies often struggle to identify and interpret malicious events reliably and transparently, particularly in cases involving unstructured or ambiguous log entries. In this work, we propose a novel methodology that combines ontology-driven structured outputs with Large Language Models (LLMs), to build an Artificial Int…

Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models
Ranjie Duan, Jiexi Liu, Xiaojun Jia, Shiji Zhao, Ruoxi Cheng, Fengxiang Wang, Cheng Wei, Yong Xie, Chang Liu, Defeng Li, Yinpeng Dong, Yichi Zhang, Yuefeng Chen, Chongwen Wang, Xingjun Ma, Xingxing Wei, Yang Liu, Hang Su, Jun Zhu, Xinfeng Li, Yitong Sun, Jie Zhang, Jinzhao Hu, Sha Xu, Yitong Yang, Jialing Tao, Hui Xue

Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models
Large language models (LLMs) typically deploy safety mechanisms to prevent harmful content generation. Most current approaches focus narrowly on risks posed by malicious actors, often framing risks as adversarial events and relying on defensive refusals. However, in real-world settings, risks also come from non-malicious users seeking help while under psychological distress (e.g., self-harm intentions). In such cases, the model's response can strongly influence the user's next actions. Simple r…

This https://arxiv.org/abs/2503.16167 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models
State-of-the-art large language models (LLMs) have demonstrated impressive code generation capabilities but struggle with real-world software engineering tasks, such as revising source code to address code reviews, hindering their practical use. Code review comments are often implicit, ambiguous, and colloquial, requiring models to grasp both code and human intent. This challenge calls for evaluating large language models' ability to bridge both technical and conversational contexts. While exis…

Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance
Yang Zhang, Chenwei Wang, Ouyang Lu, Yuan Zhao, Yunfei Ge, Zhenglong Sun, Xiu Li, Chi Zhang, Chenjia Bai, Xuelong Li
https://arxiv.org/abs/2509.02055

Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance
Vision-Language-Action (VLA) models pre-trained on large, diverse datasets show remarkable potential for general-purpose robotic manipulation. However, a primary bottleneck remains in adapting these models to downstream tasks, especially when the robot's embodiment or the task itself differs from the pre-training data. This discrepancy leads to a significant mismatch in action distributions, demanding extensive data and compute for effective fine-tuning. To address this challenge, we introduce …

Application Of Large Language Models For The Extraction Of Information From Particle Accelerator Technical Documentation
Qing Dai, Rasmus Ischebeck, Maruisz Sapinski, Adam Grycner
https://arxiv.org/abs/2509.02227

Application Of Large Language Models For The Extraction Of Information From Particle Accelerator Technical Documentation
The large set of technical documentation of legacy accelerator systems, coupled with the retirement of experienced personnel, underscores the urgent need for efficient methods to preserve and transfer specialized knowledge. This paper explores the application of large language models (LLMs), to automate and enhance the extraction of information from particle accelerator technical documents. By exploiting LLMs, we aim to address the challenges of knowledge retention, enabling the retrieval of do…

Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?
Zhuojun Gu, Quan Wang, Shuchu Han
https://arxiv.org/abs/2506.00751

Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?
Recent advances in Large Language Models (LLMs) highlight the need to align their behaviors with human values. A critical, yet understudied, issue is the potential divergence between an LLM's stated preferences (its reported alignment with general principles) and its revealed preferences (inferred from decisions in contextualized scenarios). Such deviations raise fundamental concerns for the interpretability, trustworthiness, reasoning transparency, and ethical deployment of LLMs, particularly …

This https://arxiv.org/abs/2505.18889 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Security Concerns for Large Language Models: A Survey
Large Language Models (LLMs) such as GPT-4 (and its recent iterations like GPT-4o and the GPT-4.1 series), Google's Gemini, Anthropic's Claude 3 models, and xAI's Grok have caused a revolution in natural language processing, but their capabilities also introduce new security vulnerabilities. In this survey, we provide a comprehensive overview of the emerging security concerns around LLMs, categorizing threats into prompt injection and jailbreaking, adversarial attacks (including input perturbat…

Esoteric Language Models
Subham Sekhar Sahoo, Zhihan Yang, Yash Akhauri, Johnna Liu, Deepansha Singh, Zhoujun Cheng, Zhengzhong Liu, Eric Xing, John Thickstun, Arash Vahdat
https://arxiv.org/abs/2506.01928

Esoteric Language Models
Diffusion-based language models offer a compelling alternative to autoregressive (AR) models by enabling parallel and controllable generation. Among this family of models, Masked Diffusion Models (MDMs) achieve the strongest performance but still underperform AR models in perplexity and lack key inference-time efficiency features--most notably, KV caching. In this work, we introduce Eso-LMs, a new family of models that fuses AR and MDM paradigms, enabling smooth interpolation between their perp…

CoP: Agentic Red-teaming for Large Language Models using Composition of Principles
Chen Xiong, Pin-Yu Chen, Tsung-Yi Ho
https://arxiv.org/abs/2506.00781 ht…

CoP: Agentic Red-teaming for Large Language Models using Composition of Principles
Recent advances in Large Language Models (LLMs) have spurred transformative applications in various domains, ranging from open-source to proprietary LLMs. However, jailbreak attacks, which aim to break safety alignment and user compliance by tricking the target LLMs into answering harmful and risky responses, are becoming an urgent concern. The practice of red-teaming for LLMs is to proactively explore potential risks and error-prone instances before the release of frontier AI technology. This …

LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks
Yi Yang, Jiaxuan Sun, Siqi Kou, Yihan Wang, Zhijie Deng
https://arxiv.org/abs/2506.00411

LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks
Real-world embodied agents face long-horizon tasks, characterized by high-level goals demanding multi-step solutions beyond single actions. Successfully navigating these requires both high-level task planning (i.e., decomposing goals into sub-tasks) and low-level motion control (i.e., generating precise robot actions). While existing vision language action (VLA) models and hierarchical architectures offer potential in embodied tasks, the former often falter in planning, and the latter can suffe…

An Automated Attack Investigation Approach Leveraging Threat-Knowledge-Augmented Large Language Models
Rujie Dai, Peizhuo Lv, Yujiang Gui, Qiujian Lv, Yuanyuan Qiao, Yan Wang, Degang Sun, Weiqing Huang, Yingjiu Li, XiaoFeng Wang
https://arxiv.org/abs/2509.01271

An Automated Attack Investigation Approach Leveraging Threat-Knowledge-Augmented Large Language Models
Advanced Persistent Threats (APTs) are prolonged, stealthy intrusions by skilled adversaries that compromise high-value systems to steal data or disrupt operations. Reconstructing complete attack chains from massive, heterogeneous logs is essential for effective attack investigation, yet existing methods suffer from poor platform generality, limited generalization to evolving tactics, and an inability to produce analyst-ready reports. Large Language Models (LLMs) offer strong semantic understan…

Implicit Reasoning in Large Language Models: A Comprehensive Survey
Jindong Li, Yali Fu, Li Fan, Jiahong Liu, Yao Shu, Chengwei Qin, Menglin Yang, Irwin King, Rex Ying
https://arxiv.org/abs/2509.02350 …

Implicit Reasoning in Large Language Models: A Comprehensive Survey
Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks. Reasoning with LLMs is central to solving multi-step problems and complex decision-making. To support efficient reasoning, recent studies have shifted attention from explicit chain-of-thought prompting toward implicit reasoning, where reasoning occurs silently via latent structures without emitting intermediate textual steps. Implicit reasoning brings advantages such as lower generation cost, fast…

Hidden in Plain Sight: Probing Implicit Reasoning in Multimodal Language Models
Qianqi Yan, Hongquan Li, Shan Jiang, Yang Zhao, Xinze Guan, Ching-Chen Kuo, Xin Eric Wang
https://arxiv.org/abs/2506.00258

Hidden in Plain Sight: Probing Implicit Reasoning in Multimodal Language Models
Multimodal large language models (MLLMs) are increasingly deployed in open-ended, real-world environments where inputs are messy, underspecified, and not always trustworthy. Unlike curated benchmarks, these settings frequently involve instructions that refer to missing objects or contradictory facts, rely on ambiguous references, or request infeasible actions. In such cases, success hinges not on task execution alone, but on a model's ability to detect when something is silently wrong. This pap…

DualMap: Online Open-Vocabulary Semantic Mapping for Natural Language Navigation in Dynamic Changing Scenes
Jiajun Jiang, Yiming Zhu, Zirui Wu, Jie Song
https://arxiv.org/abs/2506.01950

DualMap: Online Open-Vocabulary Semantic Mapping for Natural Language Navigation in Dynamic Changing Scenes
We introduce DualMap, an online open-vocabulary mapping system that enables robots to understand and navigate dynamically changing environments through natural language queries. Designed for efficient semantic mapping and adaptability to changing environments, DualMap meets the essential requirements for real-world robot navigation applications. Our proposed hybrid segmentation frontend and object-level status check eliminate the costly 3D object merging required by prior methods, enabling effi…

Natural language processing for African languages
David Ifeoluwa Adelani
https://arxiv.org/abs/2507.00297 https://arxiv.org/pdf/2507.…

Natural language processing for African languages
Recent advances in word embeddings and language models use large-scale, unlabelled data and self-supervised learning to boost NLP performance. Multilingual models, often trained on web-sourced data like Wikipedia, face challenges: few low-resource languages are included, their data is often noisy, and lack of labeled datasets makes it hard to evaluate performance outside high-resource languages like English. In this dissertation, we focus on languages spoken in Sub-Saharan Africa where all the …

This https://arxiv.org/abs/2406.13948 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

CityGPT: Empowering Urban Spatial Cognition of Large Language Models
Large language models(LLMs), with their powerful language generation and reasoning capabilities, have already achieved notable success in many domains, e.g., math and code generation. However, they often fall short when tackling real-life geospatial tasks within urban environments. This limitation stems from a lack of physical world knowledge and relevant data during training. To address this gap, we propose \textit{CityGPT}, a systematic framework designed to enhance LLMs' understanding of urb…

Probing Evaluation Awareness of Language Models
Jord Nguyen, Khiem Hoang, Carlo Leonardo Attubato, Felix Hofst\"atter
https://arxiv.org/abs/2507.01786

Probing Evaluation Awareness of Language Models
Language models can distinguish between testing and deployment phases -- a capability known as evaluation awareness. This has significant safety and policy implications, potentially undermining the reliability of evaluations that are central to AI governance frameworks and voluntary industry commitments. In this paper, we study evaluation awareness in Llama-3.3-70B-Instruct. We show that linear probes can separate real-world evaluation and deployment prompts, suggesting that current models inte…

This https://arxiv.org/abs/2505.21432 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Hume: Introducing System-2 Thinking in Visual-Language-Action Model
Humans practice slow thinking before performing actual actions when handling complex tasks in the physical world. This thinking paradigm, recently, has achieved remarkable advancement in boosting Large Language Models (LLMs) to solve complex tasks in digital domains. However, the potential of slow thinking remains largely unexplored for robotic foundation models interacting with the physical world. In this work, we propose Hume: a dual-system Vision-Language-Action (VLA) model with value-guided…

CityLens: Benchmarking Large Language-Vision Models for Urban Socioeconomic Sensing
Tianhui Liu, Jie Feng, Hetian Pang, Xin Zhang, Tianjian Ouyang, Zhiyuan Zhang, Yong Li
https://arxiv.org/abs/2506.00530

CityLens: Benchmarking Large Language-Vision Models for Urban Socioeconomic Sensing
Understanding urban socioeconomic conditions through visual data is a challenging yet essential task for sustainable urban development and policy planning. In this work, we introduce $\textbf{CityLens}$, a comprehensive benchmark designed to evaluate the capabilities of large language-vision models (LLVMs) in predicting socioeconomic indicators from satellite and street view imagery. We construct a multi-modal dataset covering a total of 17 globally distributed cities, spanning 6 key domains: e…

DeepSeek performs better than other Large Language Models in Dental Cases
Hexian Zhang, Xinyu Yan, Yanqi Yang, Lijian Jin, Ping Yang, Junwen Wang
https://arxiv.org/abs/2509.02036

DeepSeek performs better than other Large Language Models in Dental Cases
Large language models (LLMs) hold transformative potential in healthcare, yet their capacity to interpret longitudinal patient narratives remains inadequately explored. Dentistry, with its rich repository of structured clinical data, presents a unique opportunity to rigorously assess LLMs' reasoning abilities. While several commercial LLMs already exist, DeepSeek, a model that gained significant attention earlier this year, has also joined the competition. This study evaluated four state-of-the…

This https://arxiv.org/abs/2406.13945 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks
As large language models (LLMs) continue to advance and gain widespread use, establishing systematic and reliable evaluation methodologies for LLMs and vision-language models (VLMs) has become essential to ensure their real-world effectiveness and reliability. There have been some early explorations about the usability of LLMs for limited urban tasks, but a systematic and scalable evaluation benchmark is still lacking. The challenge in constructing a systematic evaluation benchmark for urban re…

Jointly Reinforcing Diversity and Quality in Language Model Generations
Tianjian Li, Yiming Zhang, Ping Yu, Swarnadeep Saha, Daniel Khashabi, Jason Weston, Jack Lanchantin, Tianlu Wang
https://arxiv.org/abs/2509.02534

Jointly Reinforcing Diversity and Quality in Language Model Generations
Post-training of Large Language Models (LMs) often prioritizes accuracy and helpfulness at the expense of diversity. This creates a tension: while post-training improves response quality, it also sharpens output distributions and reduces the range of ideas, limiting the usefulness of LMs in creative and exploratory tasks such as brainstorming, storytelling, or problem solving. We address this challenge with Diversity-Aware Reinforcement Learning (DARLING), a framework that jointly optimizes for…

Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategies
Tao Xiong, Xavier Hu, Wenyan Fan, Shengyu Zhang
https://arxiv.org/abs/2507.00606

Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategies
Large language models (LLMs) excel in complex tasks through advanced prompting techniques like Chain-of-Thought (CoT) and Tree-of-Thought (ToT), but their reliance on manually crafted, task-specific prompts limits adaptability and efficiency. We introduce Mixture of Reasoning (MoR), a training framework that embeds diverse reasoning strategies into LLMs for autonomous, task-adaptive reasoning without external prompt engineering. MoR has two phases: Thought Generation, creating reasoning chain t…

This https://arxiv.org/abs/2412.05718 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

RLZero: Direct Policy Inference from Language Without In-Domain Supervision
The reward hypothesis states that all goals and purposes can be understood as the maximization of a received scalar reward signal. However, in practice, defining such a reward signal is notoriously difficult, as humans are often unable to predict the optimal behavior corresponding to a reward function. Natural language offers an intuitive alternative for instructing reinforcement learning (RL) agents, yet previous language-conditioned approaches either require costly supervision or test-time tr…

Linearly Decoding Refused Knowledge in Aligned Language Models
Aryan Shrivastava, Ari Holtzman
https://arxiv.org/abs/2507.00239 https://

Linearly Decoding Refused Knowledge in Aligned Language Models
Most commonly used language models (LMs) are instruction-tuned and aligned using a combination of fine-tuning and reinforcement learning, causing them to refuse users requests deemed harmful by the model. However, jailbreak prompts can often bypass these refusal mechanisms and elicit harmful responses. In this work, we study the extent to which information accessed via jailbreak prompts is decodable using linear probes trained on LM hidden states. We show that a great deal of initially refused …

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones
Daking Rai, Samuel Miller, Kevin Moran, Ziyu Yao
https://arxiv.org/abs/2507.00322

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones
Despite remarkable advances in coding capabilities, language models (LMs) still struggle with simple syntactic tasks such as generating balanced parentheses. In this study, we investigate the underlying mechanisms behind the persistence of these errors across LMs of varying sizes (124M-7B) to both understand and mitigate the errors. Our study reveals that LMs rely on a number of components (attention heads and FF neurons) that independently make their own predictions. While some components reli…

Impact of Fine-Tuning Methods on Memorization in Large Language Models
Jie Hou, Chuxiong Wu, Lannan Luo, Qiang Zeng
https://arxiv.org/abs/2507.00258 https:…

Impact of Fine-Tuning Methods on Memorization in Large Language Models
As the capabilities of pre-trained large language models (LLMs) continue to advance, the "pre-train and fine-tune" paradigm has become increasingly mainstream, leading to the development of various fine-tuning methods. However, the privacy risks arising from memorization during fine-tuning have received relatively little attention. To address this gap, we categorize popular fine-tuning approaches and assess their impact on memorization through the lens of membership inference attacks (MIAs). Ou…

Not All Jokes Land: Evaluating Large Language Models Understanding of Workplace Humor
Moahmmadamin Shafiei, Hamidreza Saffari
https://arxiv.org/abs/2506.01819

Not All Jokes Land: Evaluating Large Language Models Understanding of Workplace Humor
With the recent advances in Artificial Intelligence (AI) and Large Language Models (LLMs), the automation of daily tasks, like automatic writing, is getting more and more attention. Hence, efforts have focused on aligning LLMs with human values, yet humor, particularly professional industrial humor used in workplaces, has been largely neglected. To address this, we develop a dataset of professional humor statements along with features that determine the appropriateness of each statement. Our ev…

Self-ensemble: Mitigating Confidence Distortion for Large Language Models
Zicheng Xu, Guanchu Wang, Guangyao Zheng, Yu-Neng Chuang, Alexander Szalay, Xia Hu, Vladimir Braverman
https://arxiv.org/abs/2506.01951

Self-ensemble: Mitigating Confidence Distortion for Large Language Models
Although Large Language Models (LLMs) perform well in general fields, they exhibit a confidence distortion problem on multi-choice question-answering (MCQA), particularly as the number of answer choices increases. Specifically, on MCQA with many choices, LLMs suffer from under-confidence in correct predictions and over-confidence in incorrect ones, leading to a substantially degraded performance. To solve this problem, we propose Self-ensemble in this work. Our method splits the choices into se…

Eka-Eval : A Comprehensive Evaluation Framework for Large Language Models in Indian Languages
Samridhi Raj Sinha, Rajvee Sheth, Abhishek Upperwal, Mayank Singh
https://arxiv.org/abs/2507.01853

Eka-Eval : A Comprehensive Evaluation Framework for Large Language Models in Indian Languages
The rapid advancement of Large Language Models (LLMs) has intensified the need for evaluation frameworks that go beyond English centric benchmarks and address the requirements of linguistically diverse regions such as India. We present EKA-EVAL, a unified and production-ready evaluation framework that integrates over 35 benchmarks, including 10 Indic-specific datasets, spanning categories like reasoning, mathematics, tool use, long-context understanding, and reading comprehension. Compared to e…

How Do Vision-Language Models Process Conflicting Information Across Modalities?
Tianze Hua, Tian Yun, Ellie Pavlick
https://arxiv.org/abs/2507.01790 https…

How Do Vision-Language Models Process Conflicting Information Across Modalities?
AI models are increasingly required to be multimodal, integrating disparate input streams into a coherent state representation on which subsequent behaviors and actions can be based. This paper seeks to understand how such models behave when input streams present conflicting information. Focusing specifically on vision-language models, we provide inconsistent inputs (e.g., an image of a dog paired with the caption "A photo of a cat") and ask the model to report the information present in one of…

From Guidelines to Practice: A New Paradigm for Arabic Language Model Evaluation
Serry Sibaee, Omer Nacar, Adel Ammar, Yasser Al-Habashi, Abdulrahman Al-Batati, Wadii Boulila
https://arxiv.org/abs/2506.01920

From Guidelines to Practice: A New Paradigm for Arabic Language Model Evaluation
This paper addresses critical gaps in Arabic language model evaluation by establishing comprehensive theoretical guidelines and introducing a novel evaluation framework. We first analyze existing Arabic evaluation datasets, identifying significant issues in linguistic accuracy, cultural alignment, and methodological rigor. To address these limitations in LLMs, we present the Arabic Depth Mini Dataset (ADMD), a carefully curated collection of 490 challenging questions spanning ten major domains …

A Diagrammatic Calculus for a Functional Model of Natural Language Semantics
Matthieu Pierre Boyer
https://arxiv.org/abs/2507.00782 https://

A Diagrammatic Calculus for a Functional Model of Natural Language Semantics
In this paper, we study a functional programming approach to natural language semantics, allowing us to increase the expressivity of a more traditional denotation style. We will formalize a category based type and effect system, and construct a diagrammatic calculus to model parsing and handling of effects, and use it to efficiently compute the denotations for sentences.

AI Analyst: Framework and Comprehensive Evaluation of Large Language Models for Financial Time Series Report Generation
Elizabeth Fons, Elena Kochkina, Rachneet Kaur, Zhen Zeng, Berowne Hlavaty, Charese Smiley, Svitlana Vyetrenko, Manuela Veloso
https://arxiv.org/abs/2507.00718

AI Analyst: Framework and Comprehensive Evaluation of Large Language Models for Financial Time Series Report Generation
This paper explores the potential of large language models (LLMs) to generate financial reports from time series data. We propose a framework encompassing prompt engineering, model selection, and evaluation. We introduce an automated highlighting system to categorize information within the generated reports, differentiating between insights derived directly from time series data, stemming from financial reasoning, and those reliant on external knowledge. This approach aids in evaluating the fac…

Towards Temporal Knowledge-Base Creation for Fine-Grained Opinion Analysis with Language Models
Gaurav Negi, Atul Kr. Ojha, Omnia Zayed, Paul Buitelaar
https://arxiv.org/abs/2509.02363

Towards Temporal Knowledge-Base Creation for Fine-Grained Opinion Analysis with Language Models
We propose a scalable method for constructing a temporal opinion knowledge base with large language models (LLMs) as automated annotators. Despite the demonstrated utility of time-series opinion analysis of text for downstream applications such as forecasting and trend analysis, existing methodologies underexploit this potential due to the absence of temporally grounded fine-grained annotations. Our approach addresses this gap by integrating well-established opinion mining formulations into a d…

Evaluating Structured Output Robustness of Small Language Models for Open Attribute-Value Extraction from Clinical Notes
Nikita Neveditsin, Pawan Lingras, Vijay Mago
https://arxiv.org/abs/2507.01810

Evaluating Structured Output Robustness of Small Language Models for Open Attribute-Value Extraction from Clinical Notes
We present a comparative analysis of the parseability of structured outputs generated by small language models for open attribute-value extraction from clinical notes. We evaluate three widely used serialization formats: JSON, YAML, and XML, and find that JSON consistently yields the highest parseability. Structural robustness improves with targeted prompting and larger models, but declines for longer documents and certain note types. Our error analysis identifies recurring format-specific fail…

Spatial Coordinates as a Cell Language: A Multi-Sentence Framework for Imaging Mass Cytometry Analysis
Chi-Jane Chen, Yuhang Chen, Sukwon Yun, Natalie Stanley, Tianlong Chen
https://arxiv.org/abs/2506.01918

Spatial Coordinates as a Cell Language: A Multi-Sentence Framework for Imaging Mass Cytometry Analysis
Image mass cytometry (IMC) enables high-dimensional spatial profiling by combining mass cytometry's analytical power with spatial distributions of cell phenotypes. Recent studies leverage large language models (LLMs) to extract cell states by translating gene or protein expression into biological context. However, existing single-cell LLMs face two major challenges: (1) Integration of spatial information: they struggle to generalize spatial coordinates and effectively encode spatial context as …

MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining
Zhixun Chen, Ping Guo, Wenhan Han, Yifan Zhang, Binbin Liu, Haobin Lin, Fengze Liu, Yan Zhao, Bingni Zhang, Taifeng Wang, Yin Zheng, Meng Fang
https://arxiv.org/abs/2507.01785

MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining
Data quality is a critical driver of large language model performance, yet existing model-based selection methods focus almost exclusively on English. We introduce MuRating, a scalable framework that transfers high-quality English data-quality signals into a single rater for 17 target languages. MuRating aggregates multiple English "raters" via pairwise comparisons to learn unified document-quality scores,then projects these judgments through translation to train a multilingual evaluator on mon…

AdamMeme: Adaptively Probe the Reasoning Capacity of Multimodal Large Language Models on Harmfulness
Zixin Chen, Hongzhan Lin, Kaixin Li, Ziyang Luo, Zhen Ye, Guang Chen, Zhiyong Huang, Jing Ma
https://arxiv.org/abs/2507.01702

AdamMeme: Adaptively Probe the Reasoning Capacity of Multimodal Large Language Models on Harmfulness
The proliferation of multimodal memes in the social media era demands that multimodal Large Language Models (mLLMs) effectively understand meme harmfulness. Existing benchmarks for assessing mLLMs on harmful meme understanding rely on accuracy-based, model-agnostic evaluations using static datasets. These benchmarks are limited in their ability to provide up-to-date and thorough assessments, as online memes evolve dynamically. To address this, we propose AdamMeme, a flexible, agent-based evalua…

Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation
Daniil Gurgurov, Katharina Trinley, Yusser Al Ghussin, Tanja Baeumel, Josef van Genabith, Simon Ostermann
https://arxiv.org/abs/2507.22608

Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation
Large language models (LLMs) exhibit strong multilingual abilities, yet the neural mechanisms behind language-specific processing remain unclear. We analyze language-specific neurons in Llama-3.1-8B, Mistral-Nemo-12B, and Aya-Expanse-8B & 32B across 21 typologically diverse languages, identifying neurons that control language behavior. Using the Language Activation Probability Entropy (LAPE) method, we show that these neurons cluster in deeper layers, with non-Latin scripts showing greater spec…

An Ensemble Classification Approach in A Multi-Layered Large Language Model Framework for Disease Prediction
Ali Hamdi, Malak Mohamed, Rokaia Emad, Khaled Shaban
https://arxiv.org/abs/2509.02446

An Ensemble Classification Approach in A Multi-Layered Large Language Model Framework for Disease Prediction
Social telehealth has made remarkable progress in healthcare by allowing patients to post symptoms and participate in medical consultations remotely. Users frequently post symptoms on social media and online health platforms, creating a huge repository of medical data that can be leveraged for disease classification. Large language models (LLMs) such as LLAMA3 and GPT-3.5, along with transformer-based models like BERT, have demonstrated strong capabilities in processing complex medical text. In…

DRAssist: Dispute Resolution Assistance using Large Language Models
Sachin Pawar, Manoj Apte, Girish K. Palshikar, Basit Ali, Nitin Ramrakhiyani
https://arxiv.org/abs/2509.01962

DRAssist: Dispute Resolution Assistance using Large Language Models
Disputes between two parties occur in almost all domains such as taxation, insurance, banking, healthcare, etc. The disputes are generally resolved in a specific forum (e.g., consumer court) where facts are presented, points of disagreement are discussed, arguments as well as specific demands of the parties are heard, and finally a human judge resolves the dispute by often favouring one of the two parties. In this paper, we explore the use of large language models (LLMs) as assistants for the h…

Causal Prompting for Implicit Sentiment Analysis with Large Language Models
Jing Ren, Wenhao Zhou, Bowen Li, Mujie Liu, Nguyen Linh Dan Le, Jiade Cen, Liping Chen, Ziqi Xu, Xiwei Xu, Xiaodong Li
https://arxiv.org/abs/2507.00389

Causal Prompting for Implicit Sentiment Analysis with Large Language Models
Implicit Sentiment Analysis (ISA) aims to infer sentiment that is implied rather than explicitly stated, requiring models to perform deeper reasoning over subtle contextual cues. While recent prompting-based methods using Large Language Models (LLMs) have shown promise in ISA, they often rely on majority voting over chain-of-thought (CoT) reasoning paths without evaluating their causal validity, making them susceptible to internal biases and spurious correlations. To address this challenge, we …

Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models
Chengao Li, Hanyu Zhang, Yunkun Xu, Hongyan Xue, Xiang Ao, Qing He
https://arxiv.org/abs/2507.01915

Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models
Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful technique for aligning large language models (LLMs) with human preferences. However, effectively aligning LLMs with diverse human preferences remains a significant challenge, particularly when they are conflict. To address this issue, we frame human value alignment as a multi-objective optimization problem, aiming to maximize a set of potentially conflicting objectives. We introduce Gradient-Adaptive Policy Optimization…

Adaptability of ASR Models on Low-Resource Language: A Comparative Study of Whisper and Wav2Vec-BERT on Bangla
Md Sazzadul Islam Ridoy, Sumi Akter, Md. Aminur Rahman
https://arxiv.org/abs/2507.01931

Adaptability of ASR Models on Low-Resource Language: A Comparative Study of Whisper and Wav2Vec-BERT on Bangla
In recent years, neural models trained on large multilingual text and speech datasets have shown great potential for supporting low-resource languages. This study investigates the performances of two state-of-the-art Automatic Speech Recognition (ASR) models, OpenAI's Whisper (Small & Large-V2) and Facebook's Wav2Vec-BERT on Bangla, a low-resource language. We have conducted experiments using two publicly available datasets: Mozilla Common Voice-17 and OpenSLR to evaluate model performances. Th…

AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models
Snehasis Mukhopadhyay, Aryan Kasat, Shivam Dubey, Rahul Karthikeyan, Dhruv Sood, Vinija Jain, Aman Chadha, Amitava Das
https://arxiv.org/abs/2509.02133

AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models
Large Language Models (LLMs) can inadvertently reflect societal biases present in their training data, leading to harmful or prejudiced outputs. In the Indian context, our empirical evaluations across a suite of models reveal that biases around caste and religion are particularly salient. Yet, most existing mitigation strategies are Western-centric and fail to address these local nuances. We propose AMBEDKAR, a framework inspired by the egalitarian vision of Dr B. R. Ambedkar, architect of the …

Contrasting Cognitive Styles in Vision-Language Models: Holistic Attention in Japanese Versus Analytical Focus in English
Ahmed Sabir, Azinovi\v{c} Gasper, Mengsay Loem, Rajesh Sharma
https://arxiv.org/abs/2507.00700

Contrasting Cognitive Styles in Vision-Language Models: Holistic Attention in Japanese Versus Analytical Focus in English
Cross-cultural research in perception and cognition has shown that individuals from different cultural backgrounds process visual information in distinct ways. East Asians, for example, tend to adopt a holistic perspective, attending to contextual relationships, whereas Westerners often employ an analytical approach, focusing on individual objects and their attributes. In this study, we investigate whether Vision-Language Models (VLMs) trained predominantly on different languages, specifically …

Extracting OPQRST in Electronic Health Records using Large Language Models with Reasoning
Zhimeng Luo, Abhibha Gupta, Adam Frisch, Daqing He
https://arxiv.org/abs/2509.01885 htt…

Extracting OPQRST in Electronic Health Records using Large Language Models with Reasoning
The extraction of critical patient information from Electronic Health Records (EHRs) poses significant challenges due to the complexity and unstructured nature of the data. Traditional machine learning approaches often fail to capture pertinent details efficiently, making it difficult for clinicians to utilize these tools effectively in patient care. This paper introduces a novel approach to extracting the OPQRST assessment from EHRs by leveraging the capabilities of Large Language Models (LLMs…

Do Self-Supervised Speech Models Exhibit the Critical Period Effects in Language Acquisition?
Yurie Koga, Shunsuke Kando, Yusuke Miyao
https://arxiv.org/abs/2508.21210 https://

Do Self-Supervised Speech Models Exhibit the Critical Period Effects in Language Acquisition?
This paper investigates whether the Critical Period (CP) effects in human language acquisition are observed in self-supervised speech models (S3Ms). CP effects refer to greater difficulty in acquiring a second language (L2) with delayed L2 exposure onset, and greater retention of their first language (L1) with delayed L1 exposure offset. While previous work has studied these effects using textual language models, their presence in speech models remains underexplored despite the central role of …

Propaganda and Information Dissemination in the Russo-Ukrainian War: Natural Language Processing of Russian and Western Twitter Narratives
Zaur Gouliev
https://arxiv.org/abs/2506.01807

Propaganda and Information Dissemination in the Russo-Ukrainian War: Natural Language Processing of Russian and Western Twitter Narratives
The conflict in Ukraine has been not only characterised by military engagement but also by a significant information war, with social media platforms like X, formerly known as Twitter playing an important role in shaping public perception. This article provides an analysis of tweets from propaganda accounts and trusted accounts collected from the onset of the war, February 2022 until the middle of May 2022 with n=40,000 total tweets. We utilise natural language processing and machine learning a…

MaXIFE: Multilingual and Cross-lingual Instruction Following Evaluation
Yile Liu, Ziwei Ma, Xiu Jiang, Jinglu Hu, Jing Chang, Liang Li
https://arxiv.org/abs/2506.01776

MaXIFE: Multilingual and Cross-lingual Instruction Following Evaluation
With the rapid adoption of large language models (LLMs) in natural language processing, the ability to follow instructions has emerged as a key metric for evaluating their practical utility. However, existing evaluation methods often focus on single-language scenarios, overlooking the challenges and differences present in multilingual and cross-lingual contexts. To address this gap, we introduce MaXIFE: a comprehensive evaluation benchmark designed to assess instruction-following capabilities a…