Tootfinder

Breaking Language Barriers: Equitable Performance in Multilingual Language Models
Tanay Nagar, Grigorii Khvatskii, Anna Sokol, Nitesh V. Chawla
https://arxiv.org/abs/2508.12662 …

Breaking Language Barriers: Equitable Performance in Multilingual Language Models
Cutting-edge LLMs have emerged as powerful tools for multilingual communication and understanding. However, LLMs perform worse in Common Sense Reasoning (CSR) tasks when prompted in low-resource languages (LRLs) like Hindi or Swahili compared to high-resource languages (HRLs) like English. Equalizing this inconsistent access to quality LLM outputs is crucial to ensure fairness for speakers of LRLs and across diverse linguistic communities. In this paper, we propose an approach to bridge this ga…

adjnoun: Word adjacencies of David Copperfield
A network of word adjacencies of common adjectives and nouns in the novel "David Copperfield" by Charles Dickens.
This network has 112 nodes and 425 edges.
Tags: Informational, Language, Unweighted
https://networks.skewed.de/net/adjnoun

Audio Flamingo Sound-CoT Technical Report: Improving Chain-of-Thought Reasoning in Sound Understanding
Zhifeng Kong, Arushi Goel, Joao Felipe Santos, Sreyan Ghosh, Rafael Valle, Wei Ping, Bryan Catanzaro
https://arxiv.org/abs/2508.11818

Audio Flamingo Sound-CoT Technical Report: Improving Chain-of-Thought Reasoning in Sound Understanding
Chain-of-thought reasoning has demonstrated significant improvements in large language models and vision language models, yet its potential for audio language models remains largely unexplored. In this technical report, we take a preliminary step towards closing this gap. For better assessment of sound reasoning, we propose AF-Reasoning-Eval, a benchmark targeting common-sense reasoning and the ability to discriminate among closely related choices. To prepare training corpus for sound reasoning…

Qualifications for holding a conversation:
* A genuine interest in what your conversation partner has to say (Otherwise it’s a monologue).
There is no #2. Not even sharing a common language, believe it or not.

RAS-Eval: A Comprehensive Benchmark for Security Evaluation of LLM Agents in Real-World Environments
Yuchuan Fu, Xiaohan Yuan, Dongxia Wang
https://arxiv.org/abs/2506.15253

RAS-Eval: A Comprehensive Benchmark for Security Evaluation of LLM Agents in Real-World Environments
The rapid deployment of Large language model (LLM) agents in critical domains like healthcare and finance necessitates robust security frameworks. To address the absence of standardized evaluation benchmarks for these agents in dynamic environments, we introduce RAS-Eval, a comprehensive security benchmark supporting both simulated and real-world tool execution. RAS-Eval comprises 80 test cases and 3,802 attack tasks mapped to 11 Common Weakness Enumeration (CWE) categories, with tools implemen…

Using AI for User Representation: An Analysis of 83 Persona Prompts
Joni Salminen, Danial Amin, Bernard Jansen
https://arxiv.org/abs/2508.13047 https://arx…

Using AI for User Representation: An Analysis of 83 Persona Prompts
We analyzed 83 persona prompts from 27 research articles that used large language models (LLMs) to generate user personas. Findings show that the prompts predominantly generate single personas. Several prompts express a desire for short or concise persona descriptions, which deviates from the tradition of creating rich, informative, and rounded persona profiles. Text is the most common format for generated persona attributes, followed by numbers. Text and numbers are often generated together, a…

Speaking of AI, CrowdStrike came out with two big announcements today on its big shift to agentic AI.
My latest piece for CSO.
CrowdStrike bets big on agentic AI with new offerings after $290M Onum buy
https://www.csoonline.com/article/405…

CrowdStrike bets big on agentic AI with new offerings after $290M Onum buy
At its Fal.Con conference, the cybersecurity giant launched its Agentic Security Platform and Agentic Security Workforce, aiming to outpace AI-driven adversaries with real-time intelligence, automation, and a common language for defense.

Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert Placement
Tian Wu, Liming Wang, Zijian Wen, Xiaoxi Zhang, Jingpu Duan, Xianwei Zhang, Jinhang Zuo
https://arxiv.org/abs/2508.12851

Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert Placement
Mixture-of-Experts (MoE) have become a cornerstone for training and scaling large language models (LLMs), offering substantial gains in model capacity and efficiency through sparse expert activation. However, serving these models remains challenging in practice, particularly in resource-constrained edge environments, due to their large memory footprint and complex communication demands. While centralized cloud inference is common, it incurs high infrastructure costs, along with latency and priv…

EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering
Yanjun Li, Yuqian Fu, Tianwen Qian, Qi'ao Xu, Silong Dai, Danda Pani Paudel, Luc Van Gool, Xiaoling Wang
https://arxiv.org/abs/2508.10729

EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering
Recent advances in Multimodal Large Language Models (MLLMs) have significantly pushed the frontier of egocentric video question answering (EgocentricQA). However, existing benchmarks and studies are mainly limited to common daily activities such as cooking and cleaning. In contrast, real-world deployment inevitably encounters domain shifts, where target domains differ substantially in both visual style and semantic content. To bridge this gap, we introduce \textbf{EgoCross}, a comprehensive ben…

Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs
Mario Sanz-Guerrero, Minh Duc Bui, Katharina von der Wense
https://arxiv.org/abs/2509.15020

Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs
When evaluating large language models (LLMs) with multiple-choice question answering (MCQA), it is common to end the prompt with the string "Answer:" to facilitate automated answer extraction via next-token probabilities. However, there is no consensus on how to tokenize the space following the colon, often overlooked as a trivial choice. In this paper, we uncover accuracy differences of up to 11% due to this (seemingly irrelevant) tokenization variation as well as reshuffled model rankings, ra…

#DH2025 Cha's group trying to come up with generalisable workflows. Working responsibly to apply this new technology. Looking for tasks that researchers have in common, working with LLM-friendly data. Rather than using very large language models, small models do amazing work on very specific tasks.

ViScratch: Using Large Language Models and Gameplay Videos for Automated Feedback in Scratch
Yuan Si, Daming Li, Hanyuan Shi, Jialu Zhang
https://arxiv.org/abs/2509.11065 https:…

ViScratch: Using Large Language Models and Gameplay Videos for Automated Feedback in Scratch
Block-based programming environments such as Scratch are increasingly popular in programming education, in particular for young learners. While the use of blocks helps prevent syntax errors, semantic bugs remain common and difficult to debug. Existing tools for Scratch debugging rely heavily on predefined rules or user manual inputs, and crucially, they ignore the platform's inherently visual nature. We introduce ViScratch, the first multimodal feedback generation system for Scratch that leve…

Towards a Common Framework for Autoformalization
Agnieszka Mensfelt, David Tena Cucala, Santiago Franco, Angeliki Koutsoukou-Argyraki, Vince Trencsenyi, Kostas Stathis
https://arxiv.org/abs/2509.09810 …

Towards a Common Framework for Autoformalization
Autoformalization has emerged as a term referring to the automation of formalization - specifically, the formalization of mathematics using interactive theorem provers (proof assistants). Its rapid development has been driven by progress in deep learning, especially large language models (LLMs). More recently, the term has expanded beyond mathematics to describe the broader task of translating informal input into formal logical representations. At the same time, a growing body of research explo…

Humans are more gullible than LLMs in believing common psychological myths
Bevan Koopman, Guido Zuccon
https://arxiv.org/abs/2507.12296 https://

Humans are more gullible than LLMs in believing common psychological myths
Despite widespread debunking, many psychological myths remain deeply entrenched. This paper investigates whether Large Language Models (LLMs) mimic human behaviour of myth belief and explores methods to mitigate such tendencies. Using 50 popular psychological myths, we evaluate myth belief across multiple LLMs under different prompting strategies, including retrieval-augmented generation and swaying prompts. Results show that LLMs exhibit significantly lower myth belief rates than humans, thoug…

Collapse of Irrelevant Representations (CIR) Ensures Robust and Non-Disruptive LLM Unlearning
Filip Sondej, Yushi Yang
https://arxiv.org/abs/2509.11816 https://

Collapse of Irrelevant Representations (CIR) Ensures Robust and Non-Disruptive LLM Unlearning
Current unlearning techniques and safety training consistently fail to remove dangerous knowledge from language models. We analyze the root causes and propose a highly selective technique which unlearns robustly and without disrupting general performance. We perform PCA on activations and module output gradients to identify subspaces containing common representations, and collapse them before calculating unlearning updates. This way we avoid unlearning general representations, and only target…

Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction
Tao Wu, Jingyuan Chen, Wang Lin, Jian Zhan, Mengze Li, Kun Kuang, Fei Wu
https://arxiv.org/abs/2508.11184

Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction
Distractors, incorrect but plausible answer choices in multiple-choice questions (MCQs), play a critical role in educational assessment by diagnosing student misconceptions. Recent work has leveraged large language models (LLMs) to generate shared, group-level distractors by learning common error patterns across large student populations. However, such distractors often fail to capture the diverse reasoning errors of individual students, limiting their diagnostic effectiveness. To address this …

ICE memo outlines plan to deport migrants to countries where they are not citizens
Federal immigration officers may deport immigrants with as little as six hours’ notice to countries other than their own -- even if officials have not provided any assurances that the new arrivals will be safe from persecution or torture, a top official said in a memo this week.

Todd M. Lyons, the acting director of U.S. Immigration and Customs Enforcement, wrote in a memo to the ICE workforce We…

ICE memo outlines plan to deport migrants to countries where they are not citizens
The dramatic shift in policy could result in thousands of immigrants being deported to places where they lack family ties or even a common language.

adjnoun: Word adjacencies of David Copperfield
A network of word adjacencies of common adjectives and nouns in the novel "David Copperfield" by Charles Dickens.
This network has 112 nodes and 425 edges.
Tags: Informational, Language, Unweighted
https://networks.skewed.de/net/adjnoun

SafeConstellations: Steering LLM Safety to Reduce Over-Refusals Through Task-Specific Trajectory
Utsav Maskey, Sumit Yadav, Mark Dras, Usman Naseem
https://arxiv.org/abs/2508.11290

SafeConstellations: Steering LLM Safety to Reduce Over-Refusals Through Task-Specific Trajectory
LLMs increasingly exhibit over-refusal behavior, where safety mechanisms cause models to reject benign instructions that superficially resemble harmful content. This phenomena diminishes utility in production applications that repeatedly rely on common prompt templates or applications that frequently rely on LLMs for specific tasks (e.g. sentiment analysis, language translation). Through comprehensive evaluation, we demonstrate that LLMs still tend to refuse responses to harmful instructions wh…

Pyrosome: Verified Compilation for Modular Metatheory
Dustin Jamner, Gabriel Kammer, Ritam Nag, Adam Chlipala
https://arxiv.org/abs/2507.06360 https://

Pyrosome: Verified Compilation for Modular Metatheory
We present Pyrosome, a generic framework for modular language metatheory that embodies a novel approach to extensible semantics and compilation, implemented in Coq. Common techniques for semantic reasoning are often tied to the specific structures of the languages and compilers that they support. In Pyrosome, verified compilers are fully extensible, meaning that to extend a language (even with a new kind of effect) simply requires defining and verifying the compilation of the new feature, reusi…

VisFinEval: A Scenario-Driven Chinese Multimodal Benchmark for Holistic Financial Understanding
Zhaowei Liu, Xin Guo, Haotian Xia, Lingfeng Zeng, Fangqi Lou, Jinyi Niu, Mengping Li, Qi Qi, Jiahuan Li, Wei Zhang, Yinglong Wang, Weige Cai, Weining Shen, Liwen Zhang
https://arxiv.org/abs/2508.09641

VisFinEval: A Scenario-Driven Chinese Multimodal Benchmark for Holistic Financial Understanding
Multimodal large language models (MLLMs) hold great promise for automating complex financial analysis. To comprehensively evaluate their capabilities, we introduce VisFinEval, the first large-scale Chinese benchmark that spans the full front-middle-back office lifecycle of financial tasks. VisFinEval comprises 15,848 annotated question-answer pairs drawn from eight common financial image modalities (e.g., K-line charts, financial statements, official seals), organized into three hierarchical sc…

Compartmentalised Agentic Reasoning for Clinical NLI
Ma\"el Jullien, Lei Xu, Marco Valentino, Andr\'e Freitas
https://arxiv.org/abs/2509.10222 https://

Compartmentalised Agentic Reasoning for Clinical NLI
A common assumption holds that scaling data and parameters yields increasingly structured, generalisable internal representations. We interrogate this assumption in clinical natural language inference (NLI) by adopting a benchmark decomposed into four reasoning families, Causal Attribution, Compositional Grounding, Epistemic Verification, and Risk State Abstraction, and introducing CARENLI, a Compartmentalised Agentic Reasoning for Clinical NLI that separates knowledge access from principled in…

adjnoun: Word adjacencies of David Copperfield
A network of word adjacencies of common adjectives and nouns in the novel "David Copperfield" by Charles Dickens.
This network has 112 nodes and 425 edges.
Tags: Informational, Language, Unweighted
https://networks.skewed.de/net/adjnoun

Interleaving Logic and Counting
Johan van Benthem, Thomas Icard
https://arxiv.org/abs/2507.05219 https://arxiv.org/pdf/2507.05219

Interleaving Logic and Counting
Reasoning with quantifier expressions in natural language combines logical and arithmetical features, transcending strict divides between qualitative and quantitative. Our topic is this cooperation of styles as it occurs in common linguistic usage and its extension into the broader practice of natural language plus "grassroots mathematics". We begin with a brief review of first-order logic with counting operators and cardinality comparisons. This system is known to be of high complexity, and …

OpenNav: Open-World Navigation with Multimodal Large Language Models
Mingfeng Yuan, Letian Wang, Steven L. Waslander
https://arxiv.org/abs/2507.18033 https://

OpenNav: Open-World Navigation with Multimodal Large Language Models
Pre-trained large language models (LLMs) have demonstrated strong common-sense reasoning abilities, making them promising for robotic navigation and planning tasks. However, despite recent progress, bridging the gap between language descriptions and actual robot actions in the open-world, beyond merely invoking limited predefined motion primitives, remains an open challenge. In this work, we aim to enable robots to interpret and decompose complex language instructions, ultimately synthesizing a…

Finding Common Ground: Using Large Language Models to Detect Agreement in Multi-Agent Decision Conferences
Selina Heller, Mohamed Ibrahim, David Antony Selby, Sebastian Vollmer
https://arxiv.org/abs/2507.08440

Finding Common Ground: Using Large Language Models to Detect Agreement in Multi-Agent Decision Conferences
Decision conferences are structured, collaborative meetings that bring together experts from various fields to address complex issues and reach a consensus on recommendations for future actions or policies. These conferences often rely on facilitated discussions to ensure productive dialogue and collective agreement. Recently, Large Language Models (LLMs) have shown significant promise in simulating real-world scenarios, particularly through collaborative multi-agent systems that mimic group in…

MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision
Zhonghao Yan, Muxi Diao, Yuxuan Yang, Jiayuan Xu, Kaizhou Zhang, Ruoyan Jing, Lele Yang, Yanxi Liu, Kongming Liang, Zhanyu Ma
https://arxiv.org/abs/2508.08177

MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision
Accurately grounding regions of interest (ROIs) is critical for diagnosis and treatment planning in medical imaging. While multimodal large language models (MLLMs) combine visual perception with natural language, current medical-grounding pipelines still rely on supervised fine-tuning with explicit spatial hints, making them ill-equipped to handle the implicit queries common in clinical practice. This work makes three core contributions. We first define Unified Medical Reasoning Grounding (UMRG…

Fine-Tuning Code Language Models to Detect Cross-Language Bugs
Zengyang Li, Yimeng Li, Binbin Huang, Peng Liang, Ran Mo, Hui Liu, Yutao Ma
https://arxiv.org/abs/2507.21954 https…

Fine-Tuning Code Language Models to Detect Cross-Language Bugs
Multilingual programming, which involves using multiple programming languages (PLs) in a single project, is increasingly common due to its benefits. However, it introduces cross-language bugs (CLBs), which arise from interactions between different PLs and are difficult to detect by single-language bug detection tools. This paper investigates the potential of pre-trained code language models (CodeLMs) in CLB detection. We developed CLCFinder, a cross-language code identification tool, and constr…

Can Common VLMs Rival Medical VLMs? Evaluation and Strategic Insights
Yuan Zhong, Ruinan Jin, Xiaoxiao Li, Qi Dou
https://arxiv.org/abs/2506.17337 https://…

Can Common VLMs Rival Medical VLMs? Evaluation and Strategic Insights
Medical vision-language models (VLMs) leverage large-scale pretraining for diverse imaging tasks but require substantial computational and data resources. Meanwhile, common or general-purpose VLMs (e.g., CLIP, LLaVA), though not trained for medical use, show promise with fine-tuning. This raises a key question: Can efficient fine-tuned common VLMs rival generalist medical VLMs for solving specific medical imaging tasks? This study systematically evaluates common and medical VLMs across disease …

Long Context Automated Essay Scoring with Language Models
Christopher Ormerod, Gitit Kehat
https://arxiv.org/abs/2509.10417 https://arxiv.org/pdf/2509.1041…

Long Context Automated Essay Scoring with Language Models
Transformer-based language models are architecturally constrained to process text of a fixed maximum length. Essays written by higher-grade students frequently exceed the maximum allowed length for many popular open-source models. A common approach to addressing this issue when using these models for Automated Essay Scoring is to truncate the input text. This raises serious validity concerns as it undermines the model's ability to fully capture and evaluate organizational elements of the scorin…

MSU-Bench: Towards Understanding the Conversational Multi-talker Scenarios
Shuai Wang, Zhaokai Sun, Zhennan Lin, Chengyou Wang, Zhou Pan, Lei Xie
https://arxiv.org/abs/2508.08155

MSU-Bench: Towards Understanding the Conversational Multi-talker Scenarios
Spoken Language Understanding (SLU) has progressed from traditional single-task methods to large audio language model (LALM) solutions. Yet, most existing speech benchmarks focus on single-speaker or isolated tasks, overlooking the challenges posed by multi-speaker conversations that are common in real-world scenarios. We introduce MSU-Bench, a comprehensive benchmark for evaluating multi-speaker conversational understanding with a speaker-centric design. Our hierarchical framework covers four …

HierMoE: Accelerating MoE Training with Hierarchical Token Deduplication and Expert Swap
Wenxiang Lin, Xinglin Pan, Lin Zhang, Shaohuai Shi, Xuan Wang, Xiaowen Chu
https://arxiv.org/abs/2508.09591

HierMoE: Accelerating MoE Training with Hierarchical Token Deduplication and Expert Swap
The sparsely activated mixture-of-experts (MoE) transformer has become a common architecture for large language models (LLMs) due to its sparsity, which requires fewer computational demands while easily scaling the model size. In MoE models, each MoE layer requires to dynamically choose tokens to activate particular experts for computation while the activated experts may not be located in the same device or GPU as the token. However, this leads to substantial communication and load imbalances a…

UDA: Unsupervised Debiasing Alignment for Pair-wise LLM-as-a-Judge
Yang Zhang, Cunxiang Wang, Lindong Wu, Wenbo Yu, Yidong Wang, Guangsheng Bao, Jie Tang
https://arxiv.org/abs/2508.09724

UDA: Unsupervised Debiasing Alignment for Pair-wise LLM-as-a-Judge
Pairwise evaluation of Large Language Models (LLMs) is a common paradigm, but it is prone to preference bias, where judges systematically favor certain outputs, such as their own. This bias leads to inconsistent and skewed rankings across different judges. To address this, we first empirically demonstrate significant and heterogeneous biases in cross-model evaluations. We then propose UDA (Unsupervised Debiasing Alignment), a framework that reduces inter-judge disagreement by dynamically adjust…

From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context
Peyman Baghershahi, Gregoire Fournier, Pranav Nyati, Sourav Medya
https://arxiv.org/abs/2508.07117

From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context
Graph Neural Networks (GNNs) have emerged as powerful tools for learning over structured data, including text-attributed graphs, which are common in domains such as citation networks, social platforms, and knowledge graphs. GNNs are not inherently interpretable and thus, many explanation methods have been proposed. However, existing explanation methods often struggle to generate interpretable, fine-grained rationales, especially when node attributes include rich natural language. In this work, …

CORONA: A Coarse-to-Fine Framework for Graph-based Recommendation with Large Language Models
Junze Chen, Xinjie Yang, Cheng Yang, Junfei Bao, Zeyuan Guo, Yawen Li, Chuan Shi
https://arxiv.org/abs/2506.17281

CORONA: A Coarse-to-Fine Framework for Graph-based Recommendation with Large Language Models
Recommender systems (RSs) are designed to retrieve candidate items a user might be interested in from a large pool. A common approach is using graph neural networks (GNNs) to capture high-order interaction relationships. As large language models (LLMs) have shown strong capabilities across domains, researchers are exploring their use to enhance recommendation. However, prior work limits LLMs to re-ranking results or dataset augmentation, failing to utilize their power during candidate filtering…

Enhancing COBOL Code Explanations: A Multi-Agents Approach Using Large Language Models
Fangjian Lei, Jiawen Liu, Shayan Noei, Ying Zou, Derek Truong, William Alexander
https://arxiv.org/abs/2507.02182

Enhancing COBOL Code Explanations: A Multi-Agents Approach Using Large Language Models
Common Business Oriented Language (COBOL) is a programming language used to develop business applications that are widely adopted by financial, business, and government agencies. Due to its age, complexity, and declining number of COBOL developers, maintaining COBOL codebases is becoming increasingly challenging. In particular, the lack of documentation makes it difficult for new developers to effectively understand and maintain COBOL systems. Existing research utilizes large language models (L…

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…

Evaluating the Effectiveness of Large Language Models in Solving Simple Programming Tasks: A User-Centered Study
Kai Deng
https://arxiv.org/abs/2507.04043 …

Evaluating the Effectiveness of Large Language Models in Solving Simple Programming Tasks: A User-Centered Study
As large language models (LLMs) become more common in educational tools and programming environments, questions arise about how these systems should interact with users. This study investigates how different interaction styles with ChatGPT-4o (passive, proactive, and collaborative) affect user performance on simple programming tasks. I conducted a within-subjects experiment where fifteen high school students participated, completing three problems under three distinct versions of the model. Eac…

SocialNav-SUB: Benchmarking VLMs for Scene Understanding in Social Robot Navigation
Michael J. Munje, Chen Tang, Shuijing Liu, Zichao Hu, Yifeng Zhu, Jiaxun Cui, Garrett Warnell, Joydeep Biswas, Peter Stone
https://arxiv.org/abs/2509.08757

SocialNav-SUB: Benchmarking VLMs for Scene Understanding in Social Robot Navigation
Robot navigation in dynamic, human-centered environments requires socially-compliant decisions grounded in robust scene understanding. Recent Vision-Language Models (VLMs) exhibit promising capabilities such as object recognition, common-sense reasoning, and contextual understanding-capabilities that align with the nuanced requirements of social robot navigation. However, it remains unclear whether VLMs can accurately understand complex social navigation scenes (e.g., inferring the spatial-temp…

Evaluating LLMs on Chinese Idiom Translation
Cai Yang, Yao Dou, David Heineman, Xiaofeng Wu, Wei Xu
https://arxiv.org/abs/2508.10421 https://arxiv.org/pdf/…

Evaluating LLMs on Chinese Idiom Translation
Idioms, whose figurative meanings usually differ from their literal interpretations, are common in everyday language, especially in Chinese, where they often contain historical references and follow specific structural patterns. Despite recent progress in machine translation with large language models, little is known about Chinese idiom translation. In this work, we introduce IdiomEval, a framework with a comprehensive error taxonomy for Chinese idiom translation. We annotate 900 translation p…

adjnoun: Word adjacencies of David Copperfield
A network of word adjacencies of common adjectives and nouns in the novel "David Copperfield" by Charles Dickens.
This network has 112 nodes and 425 edges.
Tags: Informational, Language, Unweighted
https://networks.skewed.de/net/adjnoun

CLIPin: A Non-contrastive Plug-in to CLIP for Multimodal Semantic Alignment
Shengzhu Yang, Jiawei Du, Shuai Lu, Weihang Zhang, Ningli Wang, Huiqi Li
https://arxiv.org/abs/2508.06434

CLIPin: A Non-contrastive Plug-in to CLIP for Multimodal Semantic Alignment
Large-scale natural image-text datasets, especially those automatically collected from the web, often suffer from loose semantic alignment due to weak supervision, while medical datasets tend to have high cross-modal correlation but low content diversity. These properties pose a common challenge for contrastive language-image pretraining (CLIP): they hinder the model's ability to learn robust and generalizable representations. In this work, we propose CLIPin, a unified non-contrastive plug-in t…

The role of large language models in UI/UX design: A systematic literature review
Ammar Ahmed, Ali Shariq Imran
https://arxiv.org/abs/2507.04469 https://…

The role of large language models in UI/UX design: A systematic literature review
This systematic literature review examines the role of large language models (LLMs) in UI/UX design, synthesizing findings from 38 peer-reviewed studies published between 2022 and 2025. We identify key LLMs in use, including GPT-4, Gemini, and PaLM, and map their integration across the design lifecycle, from ideation to evaluation. Common practices include prompt engineering, human-in-the-loop workflows, and multimodal input. While LLMs are reshaping design processes, challenges such as halluci…

Dr.Copilot: A Multi-Agent Prompt Optimized Assistant for Improving Patient-Doctor Communication in Romanian
Andrei Niculae, Adrian Cosma, Cosmin Dumitrache, Emilian R\v{a}doi
https://arxiv.org/abs/2507.11299

Dr.Copilot: A Multi-Agent Prompt Optimized Assistant for Improving Patient-Doctor Communication in Romanian
Text-based telemedicine has become increasingly common, yet the quality of medical advice in doctor-patient interactions is often judged more on how advice is communicated rather than its clinical accuracy. To address this, we introduce Dr.Copilot , a multi-agent large language model (LLM) system that supports Romanian-speaking doctors by evaluating and enhancing the presentation quality of their written responses. Rather than assessing medical correctness, Dr.Copilot provides feedback along 17…

The Impact of Critique on LLM-Based Model Generation from Natural Language: The Case of Activity Diagrams
Parham Khamsepour, Mark Cole, Ish Ashraf, Sandeep Puri, Mehrdad Sabetzadeh, Shiva Nejati
https://arxiv.org/abs/2509.03463

The Impact of Critique on LLM-Based Model Generation from Natural Language: The Case of Activity Diagrams
Large Language Models (LLMs) show strong potential for automating the generation of models from natural-language descriptions. A common approach is an iterative generate-critique-refine loop, where candidate models are produced, evaluated, and updated based on detected issues. This process needs to address: (1) structural correctness - compliance with well-formedness rules - and (2) semantic alignment - accurate reflection of the intended meaning in the source text. We present LADEX (LLM-based …

CAD2DMD-SET: Synthetic Generation Tool of Digital Measurement Device CAD Model Datasets for fine-tuning Large Vision-Language Models
Jo\~ao Valente, Atabak Dehban, Rodrigo Ventura
https://arxiv.org/abs/2508.21732

CAD2DMD-SET: Synthetic Generation Tool of Digital Measurement Device CAD Model Datasets for fine-tuning Large Vision-Language Models
Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities across various multimodal tasks. They continue, however, to struggle with trivial scenarios such as reading values from Digital Measurement Devices (DMDs), particularly in real-world conditions involving clutter, occlusions, extreme viewpoints, and motion blur; common in head-mounted cameras and Augmented Reality (AR) applications. Motivated by these limitations, this work introduces CAD2DMD-SE…

LDI: Localized Data Imputation
Soroush Omidvartehrani, Davood Rafiei
https://arxiv.org/abs/2506.16616 https://arxiv.org/pdf/2506.1661…

LDI: Localized Data Imputation
Missing values are a common challenge in real-world tabular data and can significantly impair downstream analysis. While Large Language Models (LLMs) have recently shown promise in data imputation, existing methods often rely on broad, unfiltered prompts that compromise accuracy, scalability, and explainability. We introduce LDI (Localized Data Imputation), a novel framework that improves both the accuracy and transparency of LLM-based imputation by selecting a compact, contextually relevant su…

adjnoun: Word adjacencies of David Copperfield
A network of word adjacencies of common adjectives and nouns in the novel "David Copperfield" by Charles Dickens.
This network has 112 nodes and 425 edges.
Tags: Informational, Language, Unweighted
https://networks.skewed.de/net/adjnoun

An Investigation Into Secondary School Students' Debugging Behaviour in Python
Laurie Gale, Sue Sentance
https://arxiv.org/abs/2508.14833 https://arxiv…

An Investigation Into Secondary School Students' Debugging Behaviour in Python
Background and context: Debugging is a common and often frustrating challenge for beginner programmers. Understanding students' debugging processes can help us identify the difficulties and misunderstandings they possess. However, we currently have limited knowledge of how secondary students debug in a text-based language, a medium through which millions of students will learn to program in the future. Objectives: In this paper, we investigate the debugging behaviour of K-12 students learning a…

Structural Code Search using Natural Language Queries
Ben Limpanukorn, Yanjun Wang, Zach Patterson, Pranav Garg, Murali Krishna Ramanathan, Xiaofei Ma, Anoop Deoras, Miryung Kim
https://arxiv.org/abs/2507.02107

Structural Code Search using Natural Language Queries
Searching code is a common task that developers perform to understand APIs, learn common code patterns, and navigate code. Currently, developers most commonly search using keywords and regular expressions that are easy to use and widely available. Beyond keywords and regular expressions, structural code search tools allow developers to search for code based on its syntactic structure. This has numerous applications ranging from bug finding to systematically refactoring code. However, these stru…

TAGAL: Tabular Data Generation using Agentic LLM Methods
Beno\^it Ronval, Pierre Dupont, Siegfried Nijssen
https://arxiv.org/abs/2509.04152 https://arxiv.o…

TAGAL: Tabular Data Generation using Agentic LLM Methods
The generation of data is a common approach to improve the performance of machine learning tasks, among which is the training of models for classification. In this paper, we present TAGAL, a collection of methods able to generate synthetic tabular data using an agentic workflow. The methods leverage Large Language Models (LLMs) for an automatic and iterative process that uses feedback to improve the generated data without any further LLM training. The use of LLMs also allows for the addition of…

Building High-Quality Datasets for Portuguese LLMs: From Common Crawl Snapshots to Industrial-Grade Corpora
Thales Sales Almeida, Rodrigo Nogueira, Helio Pedrini
https://arxiv.org/abs/2509.08824

Building High-Quality Datasets for Portuguese LLMs: From Common Crawl Snapshots to Industrial-Grade Corpora
The performance of large language models (LLMs) is deeply influenced by the quality and composition of their training data. While much of the existing work has centered on English, there remains a gap in understanding how to construct effective training corpora for other languages. We explore scalable methods for building web-based corpora for LLMs. We apply them to build a new 120B token corpus in Portuguese that achieves competitive results to an industrial-grade corpus. Using a continual pre…

Learning the non-Markovian features of subsystem dynamics
Michele Coppola, Mari Carmen Ba\~nuls, Zala Lenar\v{c}i\v{c}
https://arxiv.org/abs/2507.14133 htt…

Learning the non-Markovian features of subsystem dynamics
The dynamics of local observables in a quantum many-body system can be formally described in the language of open systems. The problem is that the bath representing the complement of the local subsystem generally does not allow the common simplifications often crucial for such a framework. Leveraging tensor network calculations and optimization tools from machine learning, we extract and characterize the dynamical maps for single- and two-site subsystems embedded in an infinite quantum Ising ch…

ASP-FZN: A Translation-based Constraint Answer Set Solver
Thomas Eiter, Tobias Geibinger, Tobias Kaminski, Nysret Musliu, Johannes Oetsch
https://arxiv.org/abs/2507.22774 https:…

ASP-FZN: A Translation-based Constraint Answer Set Solver
We present the solver asp-fzn for Constraint Answer Set Programming (CASP), which extends ASP with linear constraints. Our approach is based on translating CASP programs into the solver-independent FlatZinc language that supports several Constraint Programming and Integer Programming backend solvers. Our solver supports a rich language of linear constraints, including some common global constraints. As for evaluation, we show that asp-fzn is competitive with state-of-the-art ASP solvers on benc…

From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs
Saad Ullah, Praneeth Balasubramanian, Wenbo Guo, Amanda Burnett, Hammond Pearce, Christopher Kruegel, Giovanni Vigna, Gianluca Stringhini
https://arxiv.org/abs/2509.01835

From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs
High-quality datasets of real-world vulnerabilities and their corresponding verifiable exploits are crucial resources in software security research. Yet such resources remain scarce, as their creation demands intensive manual effort and deep security expertise. In this paper, we present CVE-GENIE, an automated, large language model (LLM)-based multi-agent framework designed to reproduce real-world vulnerabilities, provided in Common Vulnerabilities and Exposures (CVE) format, to enable creation…

Less is More: Token-Efficient Video-QA via Adaptive Frame-Pruning and Semantic Graph Integration
Shaoguang Wang (The Hong Kong University of Science and Technology), Jianxiang He (The Hong Kong University of Science and Technology), Yijie Xu (The Hong Kong University of Science and Technology), Ziyang Chen (The Hong Kong University of Science and Technology), Weiyu Guo (The Hong Kong University of Science and Technology), Hui Xiong (The Hong Kong University of Science and Technology)

Less is More: Token-Efficient Video-QA via Adaptive Frame-Pruning and Semantic Graph Integration
The practical application of Multimodal Large Language Models (MLLMs) to Video Question Answering (Video-QA) is severely hindered by the high token cost of processing numerous video frames. While increasing the number of sampled frames is a common strategy, we observe a "less is more" phenomenon where excessive frames can paradoxically degrade performance due to context dilution. Concurrently, state-of-the-art keyframe selection methods, while effective, still yield significant temporal redunda…

Multimodal Information Retrieval for Open World with Edit Distance Weak Supervision
KMA Solaiman, Bharat Bhargava
https://arxiv.org/abs/2506.20070 https://…

Multimodal Information Retrieval for Open World with Edit Distance Weak Supervision
Existing multi-media retrieval models either rely on creating a common subspace with modality-specific representation models or require schema mapping among modalities to measure similarities among multi-media data. Our goal is to avoid the annotation overhead incurred from considering retrieval as a supervised classification task and re-use the pretrained encoders in large language models and vision tasks. We propose "FemmIR", a framework to retrieve multimodal results relevant to information …

An Agentic Model Context Protocol Framework for Medical Concept Standardization
Jaerong Ahn, Andrew Wen, Nan Wang, Heling Jia, Zhiyi Yue, Sunyang Fu, Hongfang Liu
https://arxiv.org/abs/2509.03828

An Agentic Model Context Protocol Framework for Medical Concept Standardization
The Observational Medical Outcomes Partnership (OMOP) common data model (CDM) provides a standardized representation of heterogeneous health data to support large-scale, multi-institutional research. One critical step in data standardization using OMOP CDM is the mapping of source medical terms to OMOP standard concepts, a procedure that is resource-intensive and error-prone. While large language models (LLMs) have the potential to facilitate this process, their tendency toward hallucination ma…

LLMxCPG: Context-Aware Vulnerability Detection Through Code Property Graph-Guided Large Language Models
Ahmed Lekssays, Hamza Mouhcine, Khang Tran, Ting Yu, Issa Khalil
https://arxiv.org/abs/2507.16585

LLMxCPG: Context-Aware Vulnerability Detection Through Code Property Graph-Guided Large Language Models
Software vulnerabilities present a persistent security challenge, with over 25,000 new vulnerabilities reported in the Common Vulnerabilities and Exposures (CVE) database in 2024 alone. While deep learning based approaches show promise for vulnerability detection, recent studies reveal critical limitations in terms of accuracy and robustness: accuracy drops by up to 45% on rigorously verified datasets, and performance degrades significantly under simple code modifications. This paper presents L…

AI Agents for Web Testing: A Case Study in the Wild
Naimeng Ye, Xiao Yu, Ruize Xu, Tianyi Peng, Zhou Yu
https://arxiv.org/abs/2509.05197 https://arxiv.org/…

AI Agents for Web Testing: A Case Study in the Wild
Automated web testing plays a critical role in ensuring high-quality user experiences and delivering business value. Traditional approaches primarily focus on code coverage and load testing, but often fall short of capturing complex user behaviors, leaving many usability issues undetected. The emergence of large language models (LLM) and AI agents opens new possibilities for web testing by enabling human-like interaction with websites and a general awareness of common usability problems. In thi…

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…

Who's Sorry Now: User Preferences Among Rote, Empathic, and Explanatory Apologies from LLM Chatbots
Zahra Ashktorab, Alessandra Buccella, Jason D'Cruz, Zoe Fowler, Andrew Gill, Kei Yan Leung, P. D. Magnus, John Richards, Kush R. Varshney
https://arxiv.org/abs/2507.02745

Who's Sorry Now: User Preferences Among Rote, Empathic, and Explanatory Apologies from LLM Chatbots
As chatbots driven by large language models (LLMs) are increasingly deployed in everyday contexts, their ability to recover from errors through effective apologies is critical to maintaining user trust and satisfaction. In a preregistered study with Prolific workers (N=162), we examine user preferences for three types of apologies (rote, explanatory, and empathic) issued in response to three categories of common LLM mistakes (bias, unfounded fabrication, and factual errors). We designed a pairw…

Data Diversification Methods In Alignment Enhance Math Performance In LLMs
Berkan Dokmeci, Qingyang Wu, Ben Athiwaratkun, Ce Zhang, Shuaiwen Leon Song, James Zou
https://arxiv.org/abs/2507.02173

Data Diversification Methods In Alignment Enhance Math Performance In LLMs
While recent advances in preference learning have enhanced alignment in human feedback, mathematical reasoning remains a persistent challenge. We investigate how data diversification strategies in preference optimization can improve the mathematical reasoning abilities of large language models (LLMs). We evaluate three common data generation methods: temperature sampling, Chain-of-Thought prompting, and Monte Carlo Tree Search (MCTS), and introduce Diversified-ThinkSolve (DTS), a novel structur…

Measuring How (Not Just Whether) VLMs Build Common Ground
Saki Imai, Mert \.Inan, Anthony Sicilia, Malihe Alikhani
https://arxiv.org/abs/2509.03805 https://

Measuring How (Not Just Whether) VLMs Build Common Ground
Large vision language models (VLMs) increasingly claim reasoning skills, yet current benchmarks evaluate them in single-turn or question answering settings. However, grounding is an interactive process in which people gradually develop shared understanding through ongoing communication. We introduce a four-metric suite (grounding efficiency, content alignment, lexical adaptation, and human-likeness) to systematically evaluate VLM performance in interactive grounding contexts. We deploy the suit…

Cross-lingual Data Selection Using Clip-level Acoustic Similarity for Enhancing Low-resource Automatic Speech Recognition
Shunsuke Mitsumori, Sara Kashiwagi, Keitaro Tanaka, Shigeo Morishima
https://arxiv.org/abs/2506.22194

Cross-lingual Data Selection Using Clip-level Acoustic Similarity for Enhancing Low-resource Automatic Speech Recognition
This paper presents a novel donor data selection method to enhance low-resource automatic speech recognition (ASR). While ASR performs well in high-resource languages, its accuracy declines in low-resource settings due to limited training data. A common solution is to leverage multilingual self-supervised learning (SSL) models with donor languages. However, existing methods rely on language-level similarity, overlooking clip-level variations. To address this limitation, we propose clip-wise aco…

Architecture is All You Need: Improving LLM Recommenders by Dropping the Text
Kevin Foley, Shaghayegh Agah, Kavya Priyanka Kakinada
https://arxiv.org/abs/2506.15833

Architecture is All You Need: Improving LLM Recommenders by Dropping the Text
In recent years, there has been an explosion of interest in the applications of large pre-trained language models (PLMs) to recommender systems, with many studies showing strong performance of PLMs on common benchmark datasets. PLM-based recommender models benefit from flexible and customizable prompting, an unlimited vocabulary of recommendable items, and general ``world knowledge'' acquired through pre-training on massive text corpora. While PLM-based recommenders show promise in settings whe…

adjnoun: Word adjacencies of David Copperfield
A network of word adjacencies of common adjectives and nouns in the novel "David Copperfield" by Charles Dickens.
This network has 112 nodes and 425 edges.
Tags: Informational, Language, Unweighted
https://networks.skewed.de/net/adjnoun

LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model
Yirong Sun, Yizhong Geng, Peidong Wei, Yanjun Chen, Jinghan Yang, Rongfei Chen, Wei Zhang, Xiaoyu Shen
https://arxiv.org/abs/2508.15418

LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model
The development of Large Speech-Language Models (LSLMs) has been slowed by fragmented architectures and a lack of transparency, hindering the systematic comparison and reproducibility of research. Unlike in the vision-language domain, the LSLM field suffers from the common practice of releasing model weights without their corresponding training data and configurations. To address these critical gaps, we introduce LLaSO, the first fully open, end-to-end framework for large-scale speech-language …

Benchmarking LLMs for Unit Test Generation from Real-World Functions
Dong Huang, Jie M. Zhang, Mark Harman, Qianru Zhang, Mingzhe Du, See-Kiong Ng
https://arxiv.org/abs/2508.00408

Benchmarking LLMs for Unit Test Generation from Real-World Functions
Recently, large language models (LLMs) have shown great promise in automating unit test generation, significantly reducing the manual effort required by developers. To effectively evaluate the capabilities of LLMs in this domain, it is crucial to have a well-designed benchmark that accurately reflects real-world scenarios and mitigates common pitfalls. Existing LLM test generation benchmarks are limited by two critical drawbacks: data contamination and structurally simple function code. As a re…

Finance Language Model Evaluation (FLaME)
Glenn Matlin, Mika Okamoto, Huzaifa Pardawala, Yang Yang, Sudheer Chava
https://arxiv.org/abs/2506.15846 https://…

Finance Language Model Evaluation (FLaME)
Language Models (LMs) have demonstrated impressive capabilities with core Natural Language Processing (NLP) tasks. The effectiveness of LMs for highly specialized knowledge-intensive tasks in finance remains difficult to assess due to major gaps in the methodologies of existing evaluation frameworks, which have caused an erroneous belief in a far lower bound of LMs' performance on common Finance NLP (FinNLP) tasks. To demonstrate the potential of LMs for these FinNLP tasks, we present the first…

Evaluating LLMs for Visualization Generation and Understanding
Saadiq Rauf Khan, Vinit Chandak, Sougata Mukherjea
https://arxiv.org/abs/2507.22890 https://…

Evaluating LLMs for Visualization Generation and Understanding
Information Visualization has been utilized to gain insights from complex data. In recent times, Large Language models (LLMs) have performed very well in many tasks. In this paper, we showcase the capabilities of different popular LLMs to generate code for visualization based on simple prompts. We also analyze the power of LLMs to understand some common visualizations by answering questions. Our study shows that LLMs could generate code for some simpler visualizations such as bar and pie charts…

Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning
Liang Chen, Xueting Han, Li Shen, Jing Bai, Kam-Fai Wong
https://arxiv.org/abs/2509.06948 https://

Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning
Reinforcement learning (RL) has proven effective in incentivizing the reasoning abilities of large language models (LLMs), but suffers from severe efficiency challenges due to its trial-and-error nature. While the common practice employs supervised fine-tuning (SFT) as a warm-up stage for RL, this decoupled two-stage approach limits interaction between SFT and RL, thereby constraining overall effectiveness. This study introduces a novel method for learning reasoning models that employs bilevel …

Towards Recommending Usability Improvements with Multimodal Large Language Models
Sebastian Lubos, Alexander Felfernig, Gerhard Leitner, Julian Schwazer
https://arxiv.org/abs/2508.16165

Towards Recommending Usability Improvements with Multimodal Large Language Models
Usability describes a set of essential quality attributes of user interfaces (UI) that influence human-computer interaction. Common evaluation methods, such as usability testing and inspection, are effective but resource-intensive and require expert involvement. This makes them less accessible for smaller organizations. Recent advances in multimodal LLMs offer promising opportunities to automate usability evaluation processes partly by analyzing textual, visual, and structural aspects of softwa…

adjnoun: Word adjacencies of David Copperfield
A network of word adjacencies of common adjectives and nouns in the novel "David Copperfield" by Charles Dickens.
This network has 112 nodes and 425 edges.
Tags: Informational, Language, Unweighted
https://networks.skewed.de/net/adjnoun

The Anatomy of a Personal Health Agent
A. Ali Heydari, Ken Gu, Vidya Srinivas, Hong Yu, Zhihan Zhang, Yuwei Zhang, Akshay Paruchuri, Qian He, Hamid Palangi, Nova Hammerquist, Ahmed A. Metwally, Brent Winslow, Yubin Kim, Kumar Ayush, Yuzhe Yang, Girish Narayanswamy, Maxwell A. Xu, Jake Garrison, Amy Aremnto Lee, Jenny Vafeiadou, Ben Graef, Isaac R. Galatzer-Levy, Erik Schenck, Andrew Barakat, Javier Perez, Jacqueline Shreibati, John Hernandez, Anthony Z. Faranesh, Javier L. Prieto, Conn…

The Anatomy of a Personal Health Agent
Health is a fundamental pillar of human wellness, and the rapid advancements in large language models (LLMs) have driven the development of a new generation of health agents. However, the application of health agents to fulfill the diverse needs of individuals in daily non-clinical settings is underexplored. In this work, we aim to build a comprehensive personal health agent that is able to reason about multimodal data from everyday consumer wellness devices and common personal health records, …

Time to Split: Exploring Data Splitting Strategies for Offline Evaluation of Sequential Recommenders
Danil Gusak, Anna Volodkevich, Anton Klenitskiy, Alexey Vasilev, Evgeny Frolov
https://arxiv.org/abs/2507.16289

Time to Split: Exploring Data Splitting Strategies for Offline Evaluation of Sequential Recommenders
Modern sequential recommender systems, ranging from lightweight transformer-based variants to large language models, have become increasingly prominent in academia and industry due to their strong performance in the next-item prediction task. Yet common evaluation protocols for sequential recommendations remain insufficiently developed: they often fail to reflect the corresponding recommendation task accurately, or are not aligned with real-world scenarios. Although the widely used leave-one-…

Boosting Pathology Foundation Models via Few-shot Prompt-tuning for Rare Cancer Subtyping
Dexuan He, Xiao Zhou, Wenbin Guan, Liyuan Zhang, Xiaoman Zhang, Sinuo Xu, Ge Wang, Lifeng Wang, Xiaojun Yuan, Xin Sun, Yanfeng Wang, Kun Sun, Ya Zhang, Weidi Xie
https://arxiv.org/abs/2508.15904

Boosting Pathology Foundation Models via Few-shot Prompt-tuning for Rare Cancer Subtyping
Rare cancers comprise 20-25% of all malignancies but face major diagnostic challenges due to limited expert availability-especially in pediatric oncology, where they represent over 70% of cases. While pathology vision-language (VL) foundation models show promising zero-shot capabilities for common cancer subtyping, their clinical performance for rare cancers remains limited. Existing multi-instance learning (MIL) methods rely only on visual features, overlooking cross-modal knowledge and compro…

Decision-oriented Text Evaluation
Yu-Shiang Huang, Chuan-Ju Wang, Chung-Chi Chen
https://arxiv.org/abs/2507.01923 https://arxiv.org/p…

Decision-oriented Text Evaluation
Natural language generation (NLG) is increasingly deployed in high-stakes domains, yet common intrinsic evaluation methods, such as n-gram overlap or sentence plausibility, weakly correlate with actual decision-making efficacy. We propose a decision-oriented framework for evaluating generated text by directly measuring its influence on human and large language model (LLM) decision outcomes. Using market digest texts--including objective morning summaries and subjective closing-bell analyses--as…

LLMREI: Automating Requirements Elicitation Interviews with LLMs
Alexander Korn, Samuel Gorsch, Andreas Vogelsang
https://arxiv.org/abs/2507.02564 https://…

LLMREI: Automating Requirements Elicitation Interviews with LLMs
Requirements elicitation interviews are crucial for gathering system requirements but heavily depend on skilled analysts, making them resource-intensive, susceptible to human biases, and prone to miscommunication. Recent advancements in Large Language Models present new opportunities for automating parts of this process. This study introduces LLMREI, a chat bot designed to conduct requirements elicitation interviews with minimal human intervention, aiming to reduce common interviewer errors and…

adjnoun: Word adjacencies of David Copperfield
A network of word adjacencies of common adjectives and nouns in the novel "David Copperfield" by Charles Dickens.
This network has 112 nodes and 425 edges.
Tags: Informational, Language, Unweighted
https://networks.skewed.de/net/adjnoun

NodeShield: Runtime Enforcement of Security-Enhanced SBOMs for Node.js
Eric Cornelissen, Musard Balliu
https://arxiv.org/abs/2508.13750 https://arxiv.org/p…

NodeShield: Runtime Enforcement of Security-Enhanced SBOMs for Node.js
The software supply chain is an increasingly common attack vector for malicious actors. The Node.js ecosystem has been subject to a wide array of attacks, likely due to its size and prevalence. To counter such attacks, the research community and practitioners have proposed a range of static and dynamic mechanisms, including process- and language-level sandboxing, permission systems, and taint tracking. Drawing on valuable insight from these works, this paper studies a runtime protection mechani…

DaiFu: In-Situ Crash Recovery for Deep Learning Systems
Zilong He, Pengfei Chen, Hongyu Zhang, Xiaoyun Li, Guangba Yu, Hongyang Chen, Zibin Zheng
https://arxiv.org/abs/2507.01628 …

DaiFu: In-Situ Crash Recovery for Deep Learning Systems
Deep learning (DL) systems have been widely adopted in many areas, and are becoming even more popular with the emergence of large language models. However, due to the complex software stacks involved in their development and execution, crashes are unavoidable and common. Crashes severely waste computing resources and hinder development productivity, so efficient crash recovery is crucial. Existing solutions, such as checkpoint-retry, are too heavyweight for fast recovery from crashes caused by …

Insights into User Interface Innovations from a Design Thinking Workshop at deRSE25
Maximilian Frank, Simon Lund
https://arxiv.org/abs/2508.18784 https://a…

Insights into User Interface Innovations from a Design Thinking Workshop at deRSE25
Large Language Models have become widely adopted tools due to their versatile capabilities, yet their user interfaces remain limited, often following rigid, linear interaction paradigms. In this paper, we present insights from a design thinking workshop held at the deRSE25 conference aiming at collaboratively developing innovative user interface concepts for LLMs. During the workshop, participants identified common use cases, evaluated the strengths and shortcomings of current LLM interfaces, a…

Interpretable Mnemonic Generation for Kanji Learning via Expectation-Maximization
Jaewook Lee, Alexander Scarlatos, Andrew Lan
https://arxiv.org/abs/2507.05137

Interpretable Mnemonic Generation for Kanji Learning via Expectation-Maximization
Learning Japanese vocabulary is a challenge for learners from Roman alphabet backgrounds due to script differences. Japanese combines syllabaries like hiragana with kanji, which are logographic characters of Chinese origin. Kanji are also complicated due to their complexity and volume. Keyword mnemonics are a common strategy to aid memorization, often using the compositional structure of kanji to form vivid associations. Despite recent efforts to use large language models (LLMs) to assist learn…

LLM-as-classifier: Semi-Supervised, Iterative Framework for Hierarchical Text Classification using Large Language Models
Doohee You, Andy Parisi, Zach Vander Velden, Lara Dantas Inojosa
https://arxiv.org/abs/2508.16478

LLM-as-classifier: Semi-Supervised, Iterative Framework for Hierarchical Text Classification using Large Language Models
The advent of Large Language Models (LLMs) has provided unprecedented capabilities for analyzing unstructured text data. However, deploying these models as reliable, robust, and scalable classifiers in production environments presents significant methodological challenges. Standard fine-tuning approaches can be resource-intensive and often struggle with the dynamic nature of real-world data distributions, which is common in the industry. In this paper, we propose a comprehensive, semi-supervise…

PRIMMDebug: A Debugging Teaching Aid For Secondary Students
Laurie Gale, Sue Sentance
https://arxiv.org/abs/2508.18875 https://arxiv.org/pdf/2508.18875

PRIMMDebug: A Debugging Teaching Aid For Secondary Students
Debugging is often a challenging and infuriating experience for secondary school students learning their first text-based programming language. Many students resort to ineffective debugging strategies, making success with solving errors unlikely and emotional distress common. Developing tools that encourage students to adopt a more systematic and reflective approach to debugging is therefore an important, but lacking, area of research. This paper presents PRIMMDebug, a debugging teaching aid fo…

The Digital Sous Chef -- A Comparative Study on Fine-Tuning Language Models for Recipe Generation
Shubham Pundhir, Ganesh Bagler
https://arxiv.org/abs/2508.14718 https://…

The Digital Sous Chef -- A Comparative Study on Fine-Tuning Language Models for Recipe Generation
We established a rigorous benchmark for text-based recipe generation, a fundamental task in natural language generation. We present a comprehensive comparative study contrasting a fine-tuned GPT-2 large (774M) model against the GPT-2 small (124M) model and traditional LSTM/RNN baselines on the 5-cuisine corpus from RecipeDB. Our key contribution is a targeted tokenization strategy that augments the vocabulary with 23 common fraction tokens and custom structural markers. This approach addresses …

Generalizing Verifiable Instruction Following
Valentina Pyatkin, Saumya Malik, Victoria Graf, Hamish Ivison, Shengyi Huang, Pradeep Dasigi, Nathan Lambert, Hannaneh Hajishirzi
https://arxiv.org/abs/2507.02833

Generalizing Verifiable Instruction Following
A crucial factor for successful human and AI interaction is the ability of language models or chatbots to follow human instructions precisely. A common feature of instructions are output constraints like ``only answer with yes or no" or ``mention the word `abrakadabra' at least 3 times" that the user adds to craft a more useful answer. Even today's strongest models struggle with fulfilling such constraints. We find that most models strongly overfit on a small set of verifiable constraints from …

Revisiting Active Learning under (Human) Label Variation
Cornelia Gruber, Helen Alber, Bernd Bischl, G\"oran Kauermann, Barbara Plank, Matthias A{\ss}enmacher
https://arxiv.org/abs/2507.02593

Revisiting Active Learning under (Human) Label Variation
Access to high-quality labeled data remains a limiting factor in applied supervised learning. While label variation (LV), i.e., differing labels for the same instance, is common, especially in natural language processing, annotation frameworks often still rest on the assumption of a single ground truth. This overlooks human label variation (HLV), the occurrence of plausible differences in annotations, as an informative signal. Similarly, active learning (AL), a popular approach to optimizing th…

Agentic AI for Software: thoughts from Software Engineering community
Abhik Roychoudhury
https://arxiv.org/abs/2508.17343 https://arxiv.org/pdf/2508.17343

Agentic AI for Software: thoughts from Software Engineering community
AI agents have recently shown significant promise in software engineering. Much public attention has been transfixed on the topic of code generation from Large Language Models (LLMs) via a prompt. However, software engineering is much more than programming, and AI agents go far beyond instructions given by a prompt. At the code level, common software tasks include code generation, testing, and program repair. Design level software tasks may include architecture exploration, requirements under…

Going over Fine Web with a Fine-Tooth Comb: Technical Report of Indexing Fine Web for Problematic Content Search and Retrieval
In\'es Altemir Marinas, Anastasiia Kucherenko, Andrei Kucharavy
https://arxiv.org/abs/2508.21788

Going over Fine Web with a Fine-Tooth Comb: Technical Report of Indexing Fine Web for Problematic Content Search and Retrieval
Large language models (LLMs) rely heavily on web-scale datasets like Common Crawl, which provides over 80\% of training data for some modern models. However, the indiscriminate nature of web crawling raises challenges in data quality, safety, and ethics. Despite the critical importance of training data quality, prior research on harmful content has been limited to small samples due to computational constraints. This project presents a framework for indexing and analyzing LLM training datasets u…

Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning
Zinan Tang, Xin Gao, Qizhi Pei, Zhuoshi Pan, Mengzhang Cai, Jiang Wu, Conghui He, Lijun Wu
https://arxiv.org/abs/2508.21589

Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning
Supervised Fine-Tuning (SFT) Large Language Models (LLM) fundamentally rely on high-quality training data. While data selection and data synthesis are two common strategies to improve data quality, existing approaches often face limitations in static dataset curation that fail to adapt to evolving model capabilities. In this paper, we introduce Middo, a self-evolving Model-informed dynamic data optimization framework that uses model-aware data selection and context-preserving data refinement. U…

Towards Better Requirements from the Crowd: Developer Engagement with Feature Requests in Open Source Software
Pragyan K C, Rambod Ghandiparsi, Thomas Herron, John Heaps, Mitra Bokaei Hosseini
https://arxiv.org/abs/2507.13553

Towards Better Requirements from the Crowd: Developer Engagement with Feature Requests in Open Source Software
As user demands evolve, effectively incorporating feature requests is crucial for maintaining software relevance and user satisfaction. Feature requests, typically expressed in natural language, often suffer from ambiguity or incomplete information due to communication gaps or the requester's limited technical expertise. These issues can lead to misinterpretation, faulty implementation, and reduced software quality. While seeking clarification from requesters is a common strategy to mitigate th…

Re-Representation in Sentential Relation Extraction with Sequence Routing Algorithm
Ramazan Ali Bahrami, Ramin Yahyapour
https://arxiv.org/abs/2508.21049 https://

Re-Representation in Sentential Relation Extraction with Sequence Routing Algorithm
Sentential relation extraction (RE) is an important task in natural language processing (NLP). In this paper we propose to do sentential RE with dynamic routing in capsules. We first show that the proposed approach outperform state of the art on common sentential relation extraction datasets Tacred, Tacredrev, Retacred, and Conll04. We then investigate potential reasons for its good performance on the mentioned datasets, and yet low performance on another similar, yet larger sentential RE datas…

Perspectives in Play: A Multi-Perspective Approach for More Inclusive NLP Systems
Benedetta Muscato, Lucia Passaro, Gizem Gezici, Fosca Giannotti
https://arxiv.org/abs/2506.20209 …

Perspectives in Play: A Multi-Perspective Approach for More Inclusive NLP Systems
In the realm of Natural Language Processing (NLP), common approaches for handling human disagreement consist of aggregating annotators' viewpoints to establish a single ground truth. However, prior studies show that disregarding individual opinions can lead can lead to the side effect of underrepresenting minority perspectives, especially in subjective tasks, where annotators may systematically disagree because of their preferences. Recognizing that labels reflect the diverse backgrounds, life …

When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs
Ammar Khairi, Daniel D'souza, Ye Shen, Julia Kreutzer, Sara Hooker
https://arxiv.org/abs/2506.20544

When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs
Recent advancements in large language models (LLMs) have shifted focus toward scaling inference-time compute, improving performance without retraining the model. A common approach is to sample multiple outputs in parallel, and select one of these as the final output. However, work to date has focused on English and a handful of domains such as math and code. In contrast, we are most interested in techniques that generalize across open-ended tasks, formally verifiable tasks, and across languages…

Evolutionary Feature-wise Thresholding for Binary Representation of NLP Embeddings
Soumen Sinha, Shahryar Rahnamayan, Azam Asilian Bidgoli
https://arxiv.org/abs/2507.17025

Evolutionary Feature-wise Thresholding for Binary Representation of NLP Embeddings
Efficient text embedding is crucial for large-scale natural language processing (NLP) applications, where storage and computational efficiency are key concerns. In this paper, we explore how using binary representations (barcodes) instead of real-valued features can be used for NLP embeddings derived from machine learning models such as BERT. Thresholding is a common method for converting continuous embeddings into binary representations, often using a fixed threshold across all features. We pr…

NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
NVIDIA, :, Aarti Basant, Abhijit Khairnar, Abhijit Paithankar, Abhinav Khattar, Adi Renduchintala, Adithya Renduchintala, Aditya Malte, Akhiad Bercovich, Akshay Hazare, Alejandra Rico, Aleksander Ficek, Alex Kondratenko, Alex Shaposhnikov, Ali Taghibakhshi, Amelia Barton, Ameya Sunil Mahabaleshwarkar, Amy Shen, Andrew Tao, Ann Guan, Anna Shors, Anubhav Mandarwal, Arham Mehta, Arun Venkatesan, As…

NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
We introduce Nemotron-Nano-9B-v2, a hybrid Mamba-Transformer language model designed to increase throughput for reasoning workloads while achieving state-of-the-art accuracy compared to similarly-sized models. Nemotron-Nano-9B-v2 builds on the Nemotron-H architecture, in which the majority of the self-attention layers in the common Transformer architecture are replaced with Mamba-2 layers, to achieve improved inference speed when generating the long thinking traces needed for reasoning. We crea…

Prediction is not Explanation: Revisiting the Explanatory Capacity of Mapping Embeddings
Hanna Herasimchyk, Alhassan Abdelhalim, S\"oren Laue, Michaela Regneri
https://arxiv.org/abs/2508.13729

Prediction is not Explanation: Revisiting the Explanatory Capacity of Mapping Embeddings
Understanding what knowledge is implicitly encoded in deep learning models is essential for improving the interpretability of AI systems. This paper examines common methods to explain the knowledge encoded in word embeddings, which are core elements of large language models (LLMs). These methods typically involve mapping embeddings onto collections of human-interpretable semantic features, known as feature norms. Prior work assumes that accurately predicting these semantic features from the wor…