llms

Documents about llms

• SCALE: Scientific Concept Aggregation via LLMs and Embeddings for Fine-Grained Taxonomy Extension#440429arXiv CS
• Translation Tag Team: Formal Rules and LLMs Translate More Macros Together than Apart#440444arXiv CS
• Sustainability-Focused Crypto Protocols Design Methodology for Sensors and IoT with the Deployment of LLMs.#455475NCBI PubMed Central
• Beyond FLOPs: Energy-Aware Knowledge Distillation for Sustainable LLMs on Code-Related Task#463290arXiv CS
• Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs#480072arXiv CS
• Faster, Cheaper, More Accurate: Specialised Knowledge Tracing Models Outperform LLMs#609881arXiv (All)
• $R^3$-Bench: LLMs Struggle with Resource-Rational Reasoning under Shared Budgets#617206arXiv (OAI Expanded)
• Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers#617621arXiv (OAI Expanded)
• $R^3$-Bench: LLMs Struggle with Resource-Rational Reasoning under Shared Budgets#617706arXiv (All)
• Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers#618121arXiv (All)
• Assessing LLMs' mathematical abilities requires understanding the various mechanisms of mathematical creativity#618853arXiv (OAI Expanded)
• Assessing LLMs' mathematical abilities requires understanding the various mechanisms of mathematical creativity#620532arXiv (All)
• Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift#622641arXiv CS
• AutoOR: Scalably Post-training LLMs to Autoformulate Operations Research Problems#650823arXiv (OAI Expanded)
• AutoOR: Scalably Post-training LLMs to Autoformulate Operations Research Problems#652276arXiv (All)
• GhazalBench: Canonical Verse Access in LLMs across Persian Ghazals and Shakespearean Sonnets#668451arXiv (OAI Expanded)
• GhazalBench: Canonical Verse Access in LLMs across Persian Ghazals and Shakespearean Sonnets#670516arXiv (All)
• Smart Adaptive Computing Across the Continuum: LLMs in IoT-Edge-Cloud Resource Management#673487arXiv CS
• AI’s epistemic scaffolding for trespassing: The emerging role of LLMs in interdisciplinary research#690606PhilArchive
• Do Stochastic Parrots Pine for Residual Fjords? Why Conscious LLMs would be Playwrights, not Characters#694199PhilArchive
• Reinforcement Learning from Human Feedback in LLMs: Whose Culture, Whose Values, Whose Perspectives?#707091PhilArchive
• Vulnerability Detection with Interprocedural Context in Multiple Languages: Assessing Effectiveness and Cost of Modern LLMs#2440arXiv CS
• Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs#31319arXiv CS
• The Relational Formation of Possibility: Recursive Determination and the Hidden Logic of Large Language Models (LLMs)#72832PhilArchive
• Distinguishing Mechanistic Computation from Relational Experience in LLMs: A Two-Layer Framework Based on Load Minimization Theory#118142PhilArchive
• GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling#120502arXiv CS
• Early-Stage Product Line Validation Using LLMs: A Study on Semi-Formal Blueprint Analysis#124108arXiv CS
• mcdok at SemEval-2026 Task 13: Finetuning LLMs for Detection of Machine-Generated Code#126589arXiv CS
• Spore: Efficient and Training-Free Privacy Extraction Attack on LLMs via Inference-Time Hybrid Probing#138852arXiv CS
• Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora#141572arXiv CS
• Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora#144353Papers With Code
• SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs#149328Papers With Code
• Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaboration#153072arXiv (OAI)
• The Thin Line Between Comprehension and Persuasion in LLMs#153094arXiv (OAI)
• Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs#155626arXiv (OAI)
• Towards Compute-Aware In-Switch Computing for LLMs Tensor-Parallelism on Multi-GPU Systems#168277arXiv CS
• Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code#168405arXiv CS
• LLM-generated possibilities increase blame attribution#171040OSF
• Can LLMs Interpret and Leverage Structured Linguistic Representations? A Case Study with AMRs#173268arXiv (OAI)
• Reward Is Enough: LLMs Are In-Context Reinforcement Learners#173309arXiv (OAI)
• V4FinBench: Benchmarking Tabular Foundation Models, LLMs, and Standard Methods on Corporate Bankruptcy Prediction#175248arXiv CS
• Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs#180750Papers With Code
• Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems#192387arXiv CS
• Predictable Confabulations: Factual Recall by LLMs Scales with Model Size and Topic Frequency#200475arXiv CS
• Panza: Investigating the feasibility of fully-local personalized text generation#206116ISTA Publications
• OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond#214318Papers With Code
• LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws#222575arXiv CS
• CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception#222599arXiv CS
• LLMs Are Already Good Tutors: Training-Free Prompt Optimization for Pedagogical Math Tutoring#229510arXiv CS
• Lost in Sampling: Assessing Lexical Reachability in LLMs via the Word Coverage Score (WCS)#229533arXiv CS