Tootfinder

This https://arxiv.org/abs/2409.18858 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Predicting memorization within Large Language Models fine-tuned for classification
Large Language Models have received significant attention due to their abilities to solve a wide range of complex tasks. However these models memorize a significant proportion of their training data, posing a serious threat when disclosed at inference time. To mitigate this unintended memorization, it is crucial to understand what elements are memorized and why. This area of research is largely unexplored, with most existing works providing a posteriori explanations. To address this gap, we pro…

This https://arxiv.org/abs/2505.19887 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

Deconstructing Obfuscation: A four-dimensional framework for evaluating Large Language Models assembly code deobfuscation capabilities
Large language models (LLMs) have shown promise in software engineering, yet their effectiveness for binary analysis remains unexplored. We present the first comprehensive evaluation of commercial LLMs for assembly code deobfuscation. Testing seven state-of-the-art models against four obfuscation scenarios (bogus control flow, instruction substitution, control flow flattening, and their combination), we found striking performance variations--from autonomous deobfuscation to complete failure. We…

This https://arxiv.org/abs/2501.05460 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDC_…

Efficiently Serving Large Multimodal Models Using EPD Disaggregation
Large Multimodal Models (LMMs) extend Large Language Models (LLMs) by handling diverse inputs such as images, audio, and video, but at the cost of adding a multimodal encoding stage that increases both computational and memory overhead. This step negatively affects key Service Level Objectives (SLOs), such as time to first token (TTFT) and time per output token (TPOT). We introduce Encode-Prefill-Decode (EPD) Disaggregation, a novel framework that separates the encoding, prefill, and decode sta…

X changes its developer agreement to prevent third parties from using "the X API or X Content to fine-tune or train a foundation or frontier model" (Ivan Mehta/TechCrunch)
https://techcrunch.com/2025/06/05/x-changes-i…

X changes its terms to bar training of AI models using its content | TechCrunch
Social network X has changed its developer agreement to prevent third parties from using the platform's content to train large language models.

This https://arxiv.org/abs/2505.21091 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)
System prompts in Large Language Models (LLMs) are predefined directives that guide model behaviour, taking precedence over user inputs in text processing and generation. LLM deployers increasingly use them to ensure consistent responses across contexts. While model providers set a foundation of system prompts, deployers and third-party developers can append additional prompts without visibility into others' additions, while this layered implementation remains entirely hidden from end-users. As…

This https://arxiv.org/abs/2505.16933 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
In this work, we introduce LLaDA-V, a purely diffusion-based Multimodal Large Language Model (MLLM) that integrates visual instruction tuning with masked diffusion models, representing a departure from the autoregressive paradigms dominant in current multimodal approaches. Built upon LLaDA, a representative large language diffusion model, LLaDA-V incorporates a vision encoder and MLP connector that projects visual features into the language embedding space, enabling effective multimodal alignme…

This https://arxiv.org/abs/2410.06415 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

Biased AI can Influence Political Decision-Making
As modern large language models (LLMs) become integral to everyday tasks, concerns about their inherent biases and their potential impact on human decision-making have emerged. While bias in models are well-documented, less is known about how these biases influence human decisions. This paper presents two interactive experiments investigating the effects of partisan bias in LLMs on political opinions and decision-making. Participants interacted freely with either a biased liberal, biased conser…

A Framework Leveraging Large Language Models for Autonomous UAV Control in Flying Networks
Diana Nunes, Ricardo Amorim, Pedro Ribeiro, Andr\'e Coelho, Rui Campos
https://arxiv.org/abs/2506.04404

A Framework Leveraging Large Language Models for Autonomous UAV Control in Flying Networks
This paper proposes FLUC, a modular framework that integrates open-source Large Language Models (LLMs) with Unmanned Aerial Vehicle (UAV) autopilot systems to enable autonomous control in Flying Networks (FNs). FLUC translates high-level natural language commands into executable UAV mission code, bridging the gap between operator intent and UAV behaviour. FLUC is evaluated using three open-source LLMs - Qwen 2.5, Gemma 2, and LLaMA 3.2 - across scenarios involving code generation and mission …

This https://arxiv.org/abs/2503.00555 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable
Safety alignment is an important procedure before the official deployment of a Large Language Model (LLM). While safety alignment has been extensively studied for LLM, there is still a large research gap for Large Reasoning Models (LRMs) that equip with improved reasoning capability. We in this paper systematically examine a simplified pipeline for producing safety aligned LRMs. With our evaluation of various LRMs, we deliver two main findings: i) Safety alignment can be done upon the LRM to re…

What does the death of Julius Caesar and probability have to do with the future of knowledge? Join me at noon EDT today for a webinar on how AI, like a JPEG, compresses information, risking a future where history is endlessly rewritten https://maine.zoom.us/webinar/register

Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansion
Lingyuan Liu, Mengxiang Zhang
https://arxiv.org/abs/2506.04760

Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansion
Large Language Models (LLMs) have shown potential in generating hypothetical documents for query expansion, thereby enhancing information retrieval performance. However, the efficacy of this method is highly dependent on the quality of the generated documents, which often requires complex prompt strategies and the integration of advanced dense retrieval techniques. This can be both costly and computationally intensive. To mitigate these limitations, we explore the use of zero-shot LLM-based que…

Understanding Physical Properties of Unseen Deformable Objects by Leveraging Large Language Models and Robot Actions
Changmin Park, Beomjoon Lee, Haechan Jung, Haejin Jung, Changjoo Nam
https://arxiv.org/abs/2506.03760

Understanding Physical Properties of Unseen Deformable Objects by Leveraging Large Language Models and Robot Actions
In this paper, we consider the problem of understanding the physical properties of unseen objects through interactions between the objects and a robot. Handling unseen objects with special properties such as deformability is challenging for traditional task and motion planning approaches as they are often with the closed world assumption. Recent results in Large Language Models (LLMs) based task planning have shown the ability to reason about unseen objects. However, most studies assume rigid o…

This https://arxiv.org/abs/2506.02139 has been replaced.
link: https://scholar.google.com/scholar?q=a

The Unified Cognitive Consciousness Theory for Language Models: Anchoring Semantics, Thresholds of Activation, and Emergent Reasoning
Few-shot learning in large language models (LLMs) reveals a core paradox: certain tasks generalize from just a few examples, while others demand extensive supervision. To explain this, we introduce the Unified Cognitive Consciousness Theory (UCCT), which reconceptualizes LLMs not as deficient agents, but as unconscious substrates: dense, distributed repositories of linguistic and conceptual patterns that operate without explicit semantics, intention, or goal-directed reasoning. Under this view,…

This https://arxiv.org/abs/2505.22251 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Evaluation of LLMs in Speech is Often Flawed: Test Set Contamination in Large Language Models for Speech Recognition
Recent work suggests that large language models (LLMs) can improve performance of speech tasks compared to existing systems. To support their claims, results on LibriSpeech and Common Voice are often quoted. However, this work finds that a substantial amount of the LibriSpeech and Common Voice evaluation sets appear in public LLM pretraining corpora. This calls into question the reliability of findings drawn from these two datasets. To measure the impact of contamination, LLMs trained with or w…

Evaluating Prompt-Driven Chinese Large Language Models: The Influence of Persona Assignment on Stereotypes and Safeguards
Geng Liu, Li Feng, Carlo Alberto Bono, Songbo Yang, Mengxiao Zhu, Francesco Pierri
https://arxiv.org/abs/2506.04975

Evaluating Prompt-Driven Chinese Large Language Models: The Influence of Persona Assignment on Stereotypes and Safeguards
Recent research has highlighted that assigning specific personas to large language models (LLMs) can significantly increase harmful content generation. Yet, limited attention has been given to persona-driven toxicity in non-Western contexts, particularly in Chinese-based LLMs. In this paper, we perform a large-scale, systematic analysis of how persona assignment influences refusal behavior and response toxicity in Qwen, a widely-used Chinese language model. Utilizing fine-tuned BERT classifiers…

Our colleague Ebrahim Norouzi is presenting ConExion: Concept Extraction with Large Language Models, yoint work with Sven Hertling. Comprehensive Prompt Engineering Study of LLM-based concept extraction for domain coverage evaluation of ontologies.
arxive version: https://arxiv.org/abs/2504.12915…

ConExion: Concept Extraction with Large Language Models
In this paper, an approach for concept extraction from documents using pre-trained large language models (LLMs) is presented. Compared with conventional methods that extract keyphrases summarizing the important information discussed in a document, our approach tackles a more challenging task of extracting all present concepts related to the specific domain, not just the important ones. Through comprehensive evaluations of two widely used benchmark datasets, we demonstrate that our method improv…

This https://arxiv.org/abs/2505.09999 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDC_…

ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production
With the widespread adoption of Large Language Models (LLMs), serving LLM inference requests has become an increasingly important task, attracting active research advancements. Practical workloads play an essential role in this process: they are critical for motivating and benchmarking serving techniques and systems. However, the existing understanding of real-world LLM serving workloads is limited due to the lack of a comprehensive workload characterization. Prior analyses remain insufficient …

Benchmarking Large Language Models for Polymer Property Predictions
Sonakshi Gupta, Akhlak Mahmood, Shivank Shukla, Rampi Ramprasad
https://arxiv.org/abs/2506.02129

Benchmarking Large Language Models for Polymer Property Predictions
Machine learning has revolutionized polymer science by enabling rapid property prediction and generative design. Large language models (LLMs) offer further opportunities in polymer informatics by simplifying workflows that traditionally rely on large labeled datasets, handcrafted representations, and complex feature engineering. LLMs leverage natural language inputs through transfer learning, eliminating the need for explicit fingerprinting and streamlining training. In this study, we finetune …

Another of my forays into AI ethics is just out! This time the focus is on the ethics (or lack thereof) of Reinforcement Learning Feedback (RLF) techniques aimed at increasing the 'alignment' of LLMs.
The paper is fruit of the joint work of a great team of collaborators, among whom @… and @…

Helpful, harmless, honest? Sociotechnical limits of AI alignment and safety through Reinforcement Learning from Human Feedback - Ethics and Information Technology
This paper critically evaluates the attempts to align Artificial Intelligence (AI) systems, especially Large Language Models (LLMs), with human values and intentions through Reinforcement Learning from Feedback methods, involving either human feedback (RLHF) or AI feedback (RLAIF). Specifically, we show the shortcomings of the broadly pursued alignment goals of honesty, harmlessness, and helpfulness. Through a multidisciplinary sociotechnical critique, we examine both the theoretical underpinni…

This https://arxiv.org/abs/2505.24293 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Large Language Models are Locally Linear Mappings
We demonstrate that the inference operations of several open-weight large language models (LLMs) can be mapped to an exactly equivalent linear system for an input sequence without modifying the model weights or altering output predictions. Extending techniques from image diffusion models that exhibit local or piecewise linearity, we strategically alter the gradient computation with respect to a given input sequence for a next-token prediction such that the Jacobian of the model nearly exactly r…

This https://arxiv.org/abs/2405.08965 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csPL_…

Meaning-Typed Programming: Language Abstraction and Runtime for Model-Integrated Applications
Software development is shifting from traditional logical programming to model-integrated applications that leverage generative AI and large language models (LLMs) during runtime. However, integrating LLMs remains complex, requiring developers to manually craft prompts and process outputs. Existing tools attempt to assist with prompt engineering, but often introduce additional complexity. This paper presents Meaning-Typed Programming (MTP) model, a novel paradigm that abstracts LLM integratio…

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…

Large Language Models Can Achieve Explainable and Training-Free One-shot HRRP ATR
Lingfeng Chen, Panhe Hu, Zhiliang Pan, Qi Liu, Zhen Liu
https://arxiv.org/abs/2506.02465

Large Language Models Can Achieve Explainable and Training-Free One-shot HRRP ATR
This letter introduces a pioneering, training-free and explainable framework for High-Resolution Range Profile (HRRP) automatic target recognition (ATR) utilizing large-scale pre-trained Large Language Models (LLMs). Diverging from conventional methods requiring extensive task-specific training or fine-tuning, our approach converts one-dimensional HRRP signals into textual scattering center representations. Prompts are designed to align LLMs' semantic space for ATR via few-shot in-context learn…

This https://arxiv.org/abs/2502.18504 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice
Jailbreaking large-language models (LLMs) involves testing their robustness against adversarial prompts and evaluating their ability to withstand prompt attacks that could elicit unauthorized or malicious responses. In this paper, we present TurboFuzzLLM, a mutation-based fuzzing technique for efficiently finding a collection of effective jailbreaking templates that, when combined with harmful questions, can lead a target LLM to produce harmful responses through black-box access via user prompt…

In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration
Jiajie Fu, Haitong Tang, Arijit Khan, Sharad Mehrotra, Xiangyu Ke, Yunjun Gao
https://arxiv.org/abs/2506.02509

In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration
Entity Resolution (ER) is a fundamental data quality improvement task that identifies and links records referring to the same real-world entity. Traditional ER approaches often rely on pairwise comparisons, which can be costly in terms of time and monetary resources, especially with large datasets. Recently, Large Language Models (LLMs) have shown promising results in ER tasks. However, existing methods typically focus on pairwise matching, missing the potential of LLMs to perform clustering di…

hdl2v: A Code Translation Dataset for Enhanced LLM Verilog Generation
Charles Hong, Brendan Roberts, Huijae An, Alex Um, Advay Ratan, Yakun Sophia Shao
https://arxiv.org/abs/2506.04544

hdl2v: A Code Translation Dataset for Enhanced LLM Verilog Generation
Large language models (LLMs) are playing an increasingly large role in domains such as code generation, including hardware code generation, where Verilog is the key language. However, the amount of publicly available Verilog code pales in comparison to the amount of code available for software languages like Python. In this work, we present hdl2v ("HDL-to-Verilog"), a dataset which seeks to increase the amount of available human-written Verilog data by translating or compiling three other hardw…

This https://arxiv.org/abs/2505.24139 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

S4-Driver: Scalable Self-Supervised Driving Multimodal Large Language Modelwith Spatio-Temporal Visual Representation
The latest advancements in multi-modal large language models (MLLMs) have spurred a strong renewed interest in end-to-end motion planning approaches for autonomous driving. Many end-to-end approaches rely on human annotations to learn intermediate perception and prediction tasks, while purely self-supervised approaches--which directly learn from sensor inputs to generate planning trajectories without human annotations often underperform the state of the art. We observe a key gap in the input re…

via https://www.theguardian.com/technology/2025/may/26/large-language-models-that-power-ai-should-be-publicly-owned:
Matteo Valleriani: "It is time to build public, open-access LLMs for the humanities…

This https://arxiv.org/abs/2505.19145 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Do Large Language Models (Really) Need Statistical Foundations?
Large language models (LLMs) represent a new paradigm for processing unstructured data, with applications across an unprecedented range of domains. In this paper, we address, through two arguments, whether the development and application of LLMs would genuinely benefit from foundational contributions from the statistics discipline. First, we argue affirmatively, beginning with the observation that LLMs are inherently statistical models due to their profound data dependency and stochastic genera…

This https://arxiv.org/abs/2504.14522 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

Biased by Design: Leveraging AI Inherent Biases to Enhance Critical Thinking of News Readers
This paper explores the design of a propaganda detection tool using Large Language Models (LLMs). Acknowledging the inherent biases in AI models, especially in political contexts, we investigate how these biases might be leveraged to enhance critical thinking in news consumption. Countering the typical view of AI biases as detrimental, our research proposes strategies of user choice and personalization in response to a user's political stance, applying psychological concepts of confirmation bia…

This https://arxiv.org/abs/2505.23503 has been replaced.
link: https://scholar.google.com/scholar?q=a

Can Large Language Models Challenge CNNS in Medical Image Analysis?
This study presents a multimodal AI framework designed for precisely classifying medical diagnostic images. Utilizing publicly available datasets, the proposed system compares the strengths of convolutional neural networks (CNNs) and different large language models (LLMs). This in-depth comparative analysis highlights key differences in diagnostic performance, execution efficiency, and environmental impacts. Model evaluation was based on accuracy, F1-score, average execution time, average energ…

This https://arxiv.org/abs/2409.14202 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_eco…

Mining Causality: AI-Assisted Search for Instrumental Variables
The instrumental variables (IVs) method is a leading empirical strategy for causal inference. Finding IVs is a heuristic and creative process, and justifying its validity -- especially exclusion restrictions -- is largely rhetorical. We propose using large language models (LLMs) to search for new IVs through narratives and counterfactual reasoning, similar to how a human researcher would. The stark difference, however, is that LLMs can dramatically accelerate this process and explore an extreme…

This https://arxiv.org/abs/2307.14984 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSI_…

S$^3$: Social-network Simulation System with Large Language Model-Empowered Agents
Social network simulation plays a crucial role in addressing various challenges within social science. It offers extensive applications such as state prediction, phenomena explanation, and policy-making support, among others. In this work, we harness the formidable human-like capabilities exhibited by large language models (LLMs) in sensing, reasoning, and behaving, and utilize these qualities to construct the S$^3$ system (short for $\textbf{S}$ocial network $\textbf{S}$imulation $\textbf{S}$y…

This https://arxiv.org/abs/2505.00270 has been replaced.
initial toot: https://mastoxiv.page/@ar…

Large Language Models as AI Agents for Digital Atoms and Molecules: Catalyzing a New Era in Computational Biophysics
In computational biophysics, where molecular data is expanding rapidly and system complexity is increasing exponentially, large language models (LLMs) and agent-based systems are fundamentally reshaping the field. This perspective article examines the recent advances at the intersection of LLMs, intelligent agents, and scientific computation, with a focus on biophysical computation. Building on these advancements, we introduce ADAM (Agent for Digital Atoms and Molecules), an innovative multi-ag…

This https://arxiv.org/abs/2412.09429 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csMA_…

From Intention To Implementation: Automating Biomedical Research via LLMs
Conventional biomedical research is increasingly labor-intensive due to the exponential growth of scientific literature and datasets. Artificial intelligence (AI), particularly Large Language Models (LLMs), has the potential to revolutionize this process by automating various steps. Still, significant challenges remain, including the need for multidisciplinary expertise, logicality of experimental design, and performance measurements. This paper introduces BioResearcher, the first end-to-end au…

This https://arxiv.org/abs/2506.02658 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

Computational Thinking Reasoning in Large Language Models
While large language models (LLMs) have demonstrated remarkable reasoning capabilities, they often struggle with complex tasks that require specific thinking paradigms, such as divide-and-conquer and procedural deduction, \etc Previous researches integrate external, reliable tools to alleviate logical inconsistencies and hallucinations in LLMs' problem-solving processes. However, we argue that the root challenge is more profound: LLMs lack the complex thinking paradigms (\ie, computational thin…

ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking
Xianming Li, Aamir Shakir, Rui Huang, Julius Lipp, Jing Li
https://arxiv.org/abs/2506.03487

ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking
Reranking is fundamental to information retrieval and retrieval-augmented generation, with recent Large Language Models (LLMs) significantly advancing reranking quality. While recent advances with LLMs have significantly improved document reranking quality, current approaches primarily rely on large-scale LLMs (>7B parameters) through zero-shot prompting, presenting high computational costs. Small Language Models (SLMs) offer a promising alternative because of their efficiency, but our prelimin…

Cascadia: A Cascade Serving System for Large Language Models
Youhe Jiang, Fangcheng Fu, Wanru Zhao, Stephan Rabanser, Nicholas D. Lane, Binhang Yuan
https://arxiv.org/abs/2506.04203

Cascadia: A Cascade Serving System for Large Language Models
Recent advances in large language models (LLMs) have intensified the need to deliver both rapid responses and high-quality answers. More powerful models yield better results but incur higher inference latency, whereas smaller models are faster yet less capable. Recent work proposes balancing this latency-quality trade-off using model cascades, which route simpler queries to smaller models and more complex ones to larger models. However, enabling efficient cascade serving remains challenging. Cu…

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 …

This https://arxiv.org/abs/2505.24298 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning
Reinforcement learning (RL) has become a trending paradigm for training large language models (LLMs), particularly for reasoning tasks. Effective RL for LLMs requires massive parallelization and poses an urgent need for efficient training systems. Most existing large-scale RL systems for LLMs are synchronous by alternating generation and training in a batch setting, where the rollouts in each training batch are generated by the same (or latest) model. This stabilizes RL training but suffers fro…

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…

This https://arxiv.org/abs/2402.12208 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Language-Codec: Bridging Discrete Codec Representations and Speech Language Models
In recent years, large language models have achieved significant success in generative tasks related to speech, audio, music, and other signal domains. A crucial element of these models is the discrete acoustic codecs, which serve as an intermediate representation replacing the mel-spectrogram. However, there exist several gaps between discrete codecs and downstream speech language models. Specifically, 1) Due to the reconstruction paradigm of the Codec model and the structure of residual vecto…

Generating Automotive Code: Large Language Models for Software Development and Verification in Safety-Critical Systems
Sven Kirchner, Alois C. Knoll
https://arxiv.org/abs/2506.04038

Generating Automotive Code: Large Language Models for Software Development and Verification in Safety-Critical Systems
Developing safety-critical automotive software presents significant challenges due to increasing system complexity and strict regulatory demands. This paper proposes a novel framework integrating Generative Artificial Intelligence (GenAI) into the Software Development Lifecycle (SDLC). The framework uses Large Language Models (LLMs) to automate code generation in languages such as C++, incorporating safety-focused practices such as static verification, test-driven development and iterative refi…

This https://arxiv.org/abs/2504.17934 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

Toward a Human-Centered Evaluation Framework for Trustworthy LLM-Powered GUI Agents
The rise of Large Language Models (LLMs) has revolutionized Graphical User Interface (GUI) automation through LLM-powered GUI agents, yet their ability to process sensitive data with limited human oversight raises significant privacy and security risks. This position paper identifies three key risks of GUI agents and examines how they differ from traditional GUI automation and general autonomous agents. Despite these risks, existing evaluations focus primarily on performance, leaving privacy an…

This https://arxiv.org/abs/2501.04901 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDB_…

ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries
In recent years, large language models (LLMs) have demonstrated remarkable capabilities in comprehending and generating natural language content, attracting widespread attention in both industry and academia. An increasing number of services offer LLMs for various tasks via APIs. Different LLMs demonstrate expertise in different domains of queries (e.g., text classification queries). Meanwhile, LLMs of different scales, complexities, and performance are priced diversely. Driven by this, several…

Membership Inference Attacks on Sequence Models
Lorenzo Rossi, Michael Aerni, Jie Zhang, Florian Tram\`er
https://arxiv.org/abs/2506.05126 https://

Membership Inference Attacks on Sequence Models
Sequence models, such as Large Language Models (LLMs) and autoregressive image generators, have a tendency to memorize and inadvertently leak sensitive information. While this tendency has critical legal implications, existing tools are insufficient to audit the resulting risks. We hypothesize that those tools' shortcomings are due to mismatched assumptions. Thus, we argue that effectively measuring privacy leakage in sequence models requires leveraging the correlations inherent in sequential g…

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…

This https://arxiv.org/abs/2503.09427 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Language-Enhanced Representation Learning for Single-Cell Transcriptomics
Single-cell RNA sequencing (scRNA-seq) offers detailed insights into cellular heterogeneity. Recent advancements leverage single-cell large language models (scLLMs) for effective representation learning. These models focus exclusively on transcriptomic data, neglecting complementary biological knowledge from textual descriptions. To overcome this limitation, we propose scMMGPT, a novel multimodal framework designed for language-enhanced representation learning in single-cell transcriptomics. Un…

This https://arxiv.org/abs/2502.18470 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Spatial Reasoning Questions
Spatial reasoning remains a challenge for Large Language Models (LLMs), which struggle with spatial data retrieval and reasoning. We propose Spatial Retrieval-Augmented Generation (Spatial-RAG), a framework that extends RAG to spatial tasks by integrating sparse spatial retrieval (spatial databases) and dense semantic retrieval (LLM-based similarity). A multi-objective ranking strategy balances spatial constraints and semantic relevance, while an LLM-guided generator ensures coherent responses.…

PixCell: A generative foundation model for digital histopathology images
Srikar Yellapragada, Alexandros Graikos, Zilinghan Li, Kostas Triaridis, Varun Belagali, Saarthak Kapse, Tarak Nath Nandi, Ravi K Madduri, Prateek Prasanna, Tahsin Kurc, Rajarsi R. Gupta, Joel Saltz, Dimitris Samaras
https://arxiv.org/abs/2506.05127

PixCell: A generative foundation model for digital histopathology images
The digitization of histology slides has revolutionized pathology, providing massive datasets for cancer diagnosis and research. Contrastive self-supervised and vision-language models have been shown to effectively mine large pathology datasets to learn discriminative representations. On the other hand, generative models, capable of synthesizing realistic and diverse images, present a compelling solution to address unique problems in pathology that involve synthesizing images; overcoming annota…

Spatiotemporal Prediction of Electric Vehicle Charging Load Based on Large Language Models
Hang Fan, Mingxuan Li, Jingshi Cui, Zuhan Zhang, Wencai Run, Dunnan Liu
https://arxiv.org/abs/2506.03728

Spatiotemporal Prediction of Electric Vehicle Charging Load Based on Large Language Models
The rapid growth of EVs and the subsequent increase in charging demand pose significant challenges for load grid scheduling and the operation of EV charging stations. Effectively harnessing the spatiotemporal correlations among EV charging stations to improve forecasting accuracy is complex. To tackle these challenges, we propose EV-LLM for EV charging loads based on LLMs in this paper. EV-LLM integrates the strengths of Graph Convolutional Networks (GCNs) in spatiotemporal feature extraction w…

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…

This https://arxiv.org/abs/2502.14948 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation
Recent advances in large language models (LLMs) have improved their performance on coding benchmarks. However, improvement is plateauing due to the exhaustion of readily available high-quality data. Prior work has shown the potential of synthetic self-instruct data, but naively training on a model's own outputs can cause error accumulation, especially in coding tasks, where generalization may collapse due to overly simple or erroneous training data, highlighting the need for rigorous quality ch…

This https://arxiv.org/abs/2502.00722 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDC_…

Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs
Recent advancements in Large Language Models (LLMs) have led to increasingly diverse requests, accompanied with varying resource (compute and memory) demands to serve them. However, this in turn degrades the cost-efficiency of LLM serving as common practices primarily rely on homogeneous GPU resources. In response to this problem, this work conducts a thorough study about serving LLMs over heterogeneous GPU resources on cloud platforms. The rationale is that different GPU types exhibit distinct…

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…

This https://arxiv.org/abs/2505.23847 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Seven Security Challenges That Must be Solved in Cross-domain Multi-agent LLM Systems
Large language models (LLMs) are rapidly evolving into autonomous agents that cooperate across organizational boundaries, enabling joint disaster response, supply-chain optimization, and other tasks that demand decentralized expertise without surrendering data ownership. Yet, cross-domain collaboration shatters the unified trust assumptions behind current alignment and containment techniques. An agent benign in isolation may, when receiving messages from an untrusted peer, leak secrets or viola…

This https://arxiv.org/abs/2503.09117 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

GRU: Mitigating the Trade-off between Unlearning and Retention for Large Language Models
Large language model (LLM) unlearning has demonstrated its essential role in removing privacy and copyright-related responses, crucial for their legal and safe applications. However, the pursuit of complete unlearning often comes with substantial costs due to its compromises in their general functionality, leading to a notorious trade-off between unlearning and retention. In examining the update process for unlearning dynamically, we find gradients hold essential information for revealing this …

On the Comprehensibility of Multi-structured Financial Documents using LLMs and Pre-processing Tools
Shivani Upadhyay, Messiah Ataey, Shariyar Murtuza, Yifan Nie, Jimmy Lin
https://arxiv.org/abs/2506.05182

On the Comprehensibility of Multi-structured Financial Documents using LLMs and Pre-processing Tools
The proliferation of complex structured data in hybrid sources, such as PDF documents and web pages, presents unique challenges for current Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs) in providing accurate answers. Despite the recent advancements of MLLMs, they still often falter when interpreting intricately structured information, such as nested tables and multi-dimensional plots, leading to hallucinations and erroneous outputs. This paper explores the capabilit…

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/2505.05849 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

AGENTFUZZER: Generic Black-Box Fuzzing for Indirect Prompt Injection against LLM Agents
The strong planning and reasoning capabilities of Large Language Models (LLMs) have fostered the development of agent-based systems capable of leveraging external tools and interacting with increasingly complex environments. However, these powerful features also introduce a critical security risk: indirect prompt injection, a sophisticated attack vector that compromises the core of these agents, the LLM, by manipulating contextual information rather than direct user prompts. In this work, we pr…

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…

This https://arxiv.org/abs/2504.14522 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

Biased by Design: Leveraging AI Inherent Biases to Enhance Critical Thinking of News Readers
This paper explores the design of a propaganda detection tool using Large Language Models (LLMs). Acknowledging the inherent biases in AI models, especially in political contexts, we investigate how these biases might be leveraged to enhance critical thinking in news consumption. Countering the typical view of AI biases as detrimental, our research proposes strategies of user choice and personalization in response to a user's political stance, applying psychological concepts of confirmation bia…

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 …

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 …

EcoLoRA: Communication-Efficient Federated Fine-Tuning of Large Language Models
Han Liu, Ruoyao Wen, Srijith Nair, Jia Liu, Wenjing Lou, Chongjie Zhang, William Yeoh, Yevgeniy Vorobeychik, Ning Zhang
https://arxiv.org/abs/2506.02001

EcoLoRA: Communication-Efficient Federated Fine-Tuning of Large Language Models
To address data locality and privacy restrictions, Federated Learning (FL) has recently been adopted to fine-tune large language models (LLMs), enabling improved performance on various downstream tasks without requiring aggregated data. However, the repeated exchange of model updates in FL can result in prohibitively high communication costs, hindering the distributed learning process. To address this challenge, we propose EcoLoRA, a novel communication-efficient federated fine-tuning framework…

GOLFer: Smaller LM-Generated Documents Hallucination Filter & Combiner for Query Expansion in Information Retrieval
Lingyuan Liu, Mengxiang Zhang
https://arxiv.org/abs/2506.04762

GOLFer: Smaller LM-Generated Documents Hallucination Filter & Combiner for Query Expansion in Information Retrieval
Large language models (LLMs)-based query expansion for information retrieval augments queries with generated hypothetical documents with LLMs. However, its performance relies heavily on the scale of the language models (LMs), necessitating larger, more advanced LLMs. This approach is costly, computationally intensive, and often has limited accessibility. To address these limitations, we introduce GOLFer - Smaller LMs-Generated Documents Hallucination Filter & Combiner - a novel method leveragin…

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…

This https://arxiv.org/abs/2505.23585 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

On-Policy RL with Optimal Reward Baseline
Reinforcement learning algorithms are fundamental to align large language models with human preferences and to enhance their reasoning capabilities. However, current reinforcement learning algorithms often suffer from training instability due to loose on-policy constraints and computational inefficiency due to auxiliary models. In this work, we propose On-Policy RL with Optimal reward baseline (OPO), a novel and simplified reinforcement learning algorithm designed to address these challenges. O…

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…

This https://arxiv.org/abs/2502.15806 has been replaced.
link: https://scholar.google.com/scholar?q=a

A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos
Large Reasoning Models (LRMs) have significantly advanced beyond traditional Large Language Models (LLMs) with their exceptional logical reasoning capabilities, yet these improvements introduce heightened safety risks. When subjected to jailbreak attacks, their ability to generate more targeted and organized content can lead to greater harm. Although some studies claim that reasoning enables safer LRMs against existing LLM attacks, they overlook the inherent flaws within the reasoning process i…

Empirical Evaluation of Generalizable Automated Program Repair with Large Language Models
Viola Campos, Ridwan Shariffdeen, Adrian Ulges, Yannic Noller
https://arxiv.org/abs/2506.03283

Empirical Evaluation of Generalizable Automated Program Repair with Large Language Models
Automated Program Repair (APR) proposes bug fixes to aid developers in maintaining software. The state of the art in this domain focuses on using LLMs, leveraging their strong capabilities to comprehend specifications in natural language and to generate program code. Recent works have shown that LLMs can be used to generate repairs. However, despite the APR community's research achievements and several industry deployments in the last decade, APR still lacks the capabilities to generalize broad…

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…

Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability
Mengliang He, Jiayi Zeng, Yankai Jiang, Wei Zhang, Zeming Liu, Xiaoming Shi, Aimin Zhou
https://arxiv.org/abs/2506.02073

Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability
While large language models (LLMs) show promise in code generation, existing benchmarks neglect the flowchart-based code generation. To promote further research on flowchart-based code generation, this work presents Flow2Code, a novel benchmark for flowchart-based code generation evaluation. The evaluation dataset spans 15 programming languages and includes 5,622 code segments paired with 16,866 flowcharts of three types: code, UML, and pseudocode. Extensive experiments with 13 multimodal LLMs …

BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage
Kalyan Nakka, Nitesh Saxena
https://arxiv.org/abs/2506.02479

BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage
The inherent risk of generating harmful and unsafe content by Large Language Models (LLMs), has highlighted the need for their safety alignment. Various techniques like supervised fine-tuning, reinforcement learning from human feedback, and red-teaming were developed for ensuring the safety alignment of LLMs. However, the robustness of these aligned LLMs is always challenged by adversarial attacks that exploit unexplored and underlying vulnerabilities of the safety alignment. In this paper, we …

Memory Access Characterization of Large Language Models in CPU Environment and its Potential Impacts
Spencer Banasik
https://arxiv.org/abs/2506.01827 https…

Memory Access Characterization of Large Language Models in CPU Environment and its Potential Impacts
As machine learning algorithms are shown to be an increasingly valuable tool, the demand for their access has grown accordingly. Oftentimes, it is infeasible to run inference with larger models without an accelerator, which may be unavailable in environments that have constraints such as energy consumption, security, or cost. To increase the availability of these models, we aim to im- prove the LLM inference speed on a CPU-only environment by modifying the cache architecture. To determine what …

This https://arxiv.org/abs/2503.23487 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Large Language and Reasoning Models are Shallow Disjunctive Reasoners
Large Language Models (LLMs) have been found to struggle with systematic reasoning. Even on tasks where they appear to perform well, their performance often depends on shortcuts, rather than on genuine reasoning abilities, leading them to collapse on out-of-distribution (OOD) examples. Post-training strategies based on reinforcement learning and chain-of-thought prompting have recently been hailed as a step change. However, little is known about the potential of the resulting ``Large Reasoning …

Computational Thinking Reasoning in Large Language Models
Kechi Zhang, Ge Li, Jia Li, Huangzhao Zhang, Jingjing Xu, Hao Zhu, Lecheng Wang, Jia Li, Yihong Dong, Jing Mai, Bin Gu, Zhi Jin
https://arxiv.org/abs/2506.02658

Computational Thinking Reasoning in Large Language Models
While large language models (LLMs) have demonstrated remarkable reasoning capabilities, they often struggle with complex tasks that require specific thinking paradigms, such as divide-and-conquer and procedural deduction, \etc Previous researches integrate external, reliable tools to alleviate logical inconsistencies and hallucinations in LLMs' problem-solving processes. However, we argue that the root challenge is more profound: LLMs lack the complex thinking paradigms (\ie, computational thin…

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. …

This https://arxiv.org/abs/2501.07849 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation
Large Language Models (LLMs) have emerged as the new recommendation engines, surpassing traditional methods in both capability and scope, particularly in code generation. In this paper, we reveal a novel provider bias in LLMs: without explicit directives, these models show systematic preferences for services from specific providers in their recommendations (e.g., favoring Google Cloud over Microsoft Azure). To systematically investigate this bias, we develop an automated pipeline to construct t…

This https://arxiv.org/abs/2505.21427 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Policy Induction: Predicting Startup Success via Explainable Memory-Augmented In-Context Learning
Early-stage startup investment is a high-risk endeavor characterized by scarce data and uncertain outcomes. Traditional machine learning approaches often require large, labeled datasets and extensive fine-tuning, yet remain opaque and difficult for domain experts to interpret or improve. In this paper, we propose a transparent and data-efficient investment decision framework powered by memory-augmented large language models (LLMs) using in-context learning (ICL). Central to our method is a natu…

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…

This https://arxiv.org/abs/2409.14644 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

An Effective Approach to Embedding Source Code by Combining Large Language and Sentence Embedding Models
The advent of large language models (LLMs) has significantly advanced artificial intelligence (AI) in software engineering (SE), with source code embeddings playing a crucial role in tasks such as source code clone detection and source code clustering. However, existing methods for source code embedding, including those based on LLMs, often rely on costly supervised training or fine-tuning for domain adaptation. This paper proposes a novel approach to embedding source code by combining large la…

This https://arxiv.org/abs/2506.00486 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

It Takes a Good Model to Train a Good Model: Generalized Gaussian Priors for Optimized LLMs
Despite rapid advancements in the research and deployment of large language models (LLMs), the statistical distribution of model parameters, as well as their influence on initialization, training dynamics, and downstream efficiency, has received surprisingly little attention. A recent work introduced BackSlash, a training-time compression algorithm. It first demonstrated that pre-trained LLM parameters follow generalized Gaussian distributions (GGDs) better. By optimizing GG priors during train…

GenFair: Systematic Test Generation for Fairness Fault Detection in Large Language Models
Madhusudan Srinivasan, Jubril Abdel
https://arxiv.org/abs/2506.03024

GenFair: Systematic Test Generation for Fairness Fault Detection in Large Language Models
Large Language Models (LLMs) are increasingly deployed in critical domains, yet they often exhibit biases inherited from training data, leading to fairness concerns. This work focuses on the problem of effectively detecting fairness violations, especially intersectional biases that are often missed by existing template-based and grammar-based testing methods. Previous approaches, such as CheckList and ASTRAEA, provide structured or grammar-driven test generation but struggle with low test diver…

This https://arxiv.org/abs/2505.17433 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

MemeReaCon: Probing Contextual Meme Understanding in Large Vision-Language Models
Memes have emerged as a popular form of multimodal online communication, where their interpretation heavily depends on the specific context in which they appear. Current approaches predominantly focus on isolated meme analysis, either for harmful content detection or standalone interpretation, overlooking a fundamental challenge: the same meme can express different intents depending on its conversational context. This oversight creates an evaluation gap: although humans intuitively recognize ho…

This https://arxiv.org/abs/2505.10360 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

FactsR: A Safer Method for Producing High Quality Healthcare Documentation
There are now a multitude of AI-scribing solutions for healthcare promising the utilization of large language models for ambient documentation. However, these AI scribes still rely on one-shot, or few-shot prompts for generating notes after the consultation has ended, employing little to no reasoning. This risks long notes with an increase in hallucinations, misrepresentation of the intent of the clinician, and reliance on the proofreading of the clinician to catch errors. A dangerous combinati…

Automated Web Application Testing: End-to-End Test Case Generation with Large Language Models and Screen Transition Graphs
Nguyen-Khang Le, Quan Minh Bui, Minh Ngoc Nguyen, Hiep Nguyen, Trung Vo, Son T. Luu, Shoshin Nomura, Minh Le Nguyen
https://arxiv.org/abs/2506.02529

Automated Web Application Testing: End-to-End Test Case Generation with Large Language Models and Screen Transition Graphs
Web applications are critical to modern software ecosystems, yet ensuring their reliability remains challenging due to the complexity and dynamic nature of web interfaces. Recent advances in large language models (LLMs) have shown promise in automating complex tasks, but limitations persist in handling dynamic navigation flows and complex form interactions. This paper presents an automated system for generating test cases for two key aspects of web application testing: site navigation and form …

This https://arxiv.org/abs/2505.08459 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Strategy-Augmented Planning for Large Language Models via Opponent Exploitation
Efficiently modeling and exploiting opponents is a long-standing challenge in adversarial domains. Large Language Models (LLMs) trained on extensive textual data have recently demonstrated outstanding performance in general tasks, introducing new research directions for opponent modeling. Some studies primarily focus on directly using LLMs to generate decisions based on the elaborate prompt context that incorporates opponent descriptions, while these approaches are limited to scenarios where LL…

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…

This https://arxiv.org/abs/2506.01056 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

MCP-Zero: Proactive Toolchain Construction for LLM Agents from Scratch
Function-calling has enabled large language models (LLMs) to act as tool-using agents, but injecting thousands of tool schemas into the prompt is costly and error-prone. We introduce MCP-Zero, a proactive agent framework that lets the LLM itself decide when and which external tools to retrieve, thereby assembling a task-specific toolchain from scratch. The framework is built upon three components: (1) Proactive Tool Request, where the model emits a structured $\left<\operatorname{tool\_assistan…

This https://arxiv.org/abs/2503.04149 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination
The rapid evolution of code largelanguage models underscores the need for effective and transparent benchmarking of their reasoning capabilities. However, the current benchmarking approach heavily depends on publicly available, human-created datasets. The widespread use of these fixed benchmark datasets makes the benchmarking process to be static and thus particularly susceptible to data contamination, an unavoidable consequence of the extensive data collection processes used to train Code LLMs…

This https://arxiv.org/abs/2506.02965 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Memory-Efficient and Privacy-Preserving Collaborative Training for Mixture-of-Experts LLMs
Mixture-of-Experts (MoE) has been gaining popularity due to its successful adaptation to large language models (LLMs). In this work, we introduce Privacy-preserving Collaborative Mixture-of-Experts (PC-MoE), which leverages the sparsity of the MoE architecture for memory-efficient decentralized collaborative LLM training, enabling multiple parties with limited GPU-memory and data resources to collectively train more capable LLMs than they could achieve individually. At the same time, this appro…

This https://arxiv.org/abs/2506.00618 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

RiOSWorld: Benchmarking the Risk of Multimodal Compter-Use Agents
With the rapid development of multimodal large language models (MLLMs), they are increasingly deployed as autonomous computer-use agents capable of accomplishing complex computer tasks. However, a pressing issue arises: Can the safety risk principles designed and aligned for general MLLMs in dialogue scenarios be effectively transferred to real-world computer-use scenarios? Existing research on evaluating the safety risks of MLLM-based computer-use agents suffers from several limitations: it ei…

Across Programming Language Silos: A Study on Cross-Lingual Retrieval-augmented Code Generation
Qiming Zhu, Jialun Cao, Xuanang Chen, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun, Shing-Chi Cheung
https://arxiv.org/abs/2506.03535

Across Programming Language Silos: A Study on Cross-Lingual Retrieval-augmented Code Generation
Current research on large language models (LLMs) with retrieval-augmented code generation (RACG) mainly focuses on single-language settings, leaving cross-lingual effectiveness and security unexplored. Multi-lingual RACG systems are valuable for migrating code-bases across programming languages (PLs), yet face risks from error (e.g. adversarial data corruption) propagation in cross-lingual transfer. We construct a dataset spanning 13 PLs with nearly 14k instances to explore utility and robustne…

This https://arxiv.org/abs/2505.24034 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Trainin
Reinforcement Learning (RL) has become the most effective post-training approach for improving the capabilities of Large Language Models (LLMs). In practice, because of the high demands on latency and memory, it is particularly challenging to develop an efficient RL framework that reliably manages policy models with hundreds to thousands of billions of parameters. In this paper, we present LlamaRL, a fully distributed, asynchronous RL framework optimized for efficient training of large-scale …

This https://arxiv.org/abs/2505.10981 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory
Recently, scaling test-time compute on Large Language Models (LLM) has garnered wide attention. However, there has been limited investigation of how various reasoning prompting strategies perform as scaling. In this paper, we focus on a standard and realistic scaling setting: majority voting. We systematically conduct experiments on 6 LLMs $\times$ 8 prompting strategies $\times$ 6 benchmarks. Experiment results consistently show that as the sampling time and computational overhead increase, co…

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…

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…

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…

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…