Large Language Models

GPT, Claude, Gemini, and other LLMs

This Week's Best | Monthly Best | Guide | Trending

Top This Week

[2604.16909] PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations
Llms

[2604.16909] PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations

Abstract page for arXiv paper 2604.16909: PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations

arXiv - AI · 4 min ·
[2604.07802] Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models
Llms

[2604.07802] Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models

Abstract page for arXiv paper 2604.07802: Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models

arXiv - AI · 4 min ·
[2602.07605] Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning
Llms

[2602.07605] Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning

Abstract page for arXiv paper 2602.07605: Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Rea...

arXiv - AI · 4 min ·

All Content

[2603.04419] Context-Dependent Affordance Computation in Vision-Language Models
Llms

[2603.04419] Context-Dependent Affordance Computation in Vision-Language Models

Abstract page for arXiv paper 2603.04419: Context-Dependent Affordance Computation in Vision-Language Models

arXiv - Machine Learning · 4 min ·
[2603.04413] Simulating Meaning, Nevermore! Introducing ICR: A Semiotic-Hermeneutic Metric for Evaluating Meaning in LLM Text Summaries
Llms

[2603.04413] Simulating Meaning, Nevermore! Introducing ICR: A Semiotic-Hermeneutic Metric for Evaluating Meaning in LLM Text Summaries

Abstract page for arXiv paper 2603.04413: Simulating Meaning, Nevermore! Introducing ICR: A Semiotic-Hermeneutic Metric for Evaluating Me...

arXiv - AI · 4 min ·
[2603.04411] One Size Does Not Fit All: Token-Wise Adaptive Compression for KV Cache
Llms

[2603.04411] One Size Does Not Fit All: Token-Wise Adaptive Compression for KV Cache

Abstract page for arXiv paper 2603.04411: One Size Does Not Fit All: Token-Wise Adaptive Compression for KV Cache

arXiv - Machine Learning · 3 min ·
[2603.04410] SalamahBench: Toward Standardized Safety Evaluation for Arabic Language Models
Llms

[2603.04410] SalamahBench: Toward Standardized Safety Evaluation for Arabic Language Models

Abstract page for arXiv paper 2603.04410: SalamahBench: Toward Standardized Safety Evaluation for Arabic Language Models

arXiv - AI · 4 min ·
[2603.04409] Unpacking Human Preference for LLMs: Demographically Aware Evaluation with the HUMAINE Framework
Llms

[2603.04409] Unpacking Human Preference for LLMs: Demographically Aware Evaluation with the HUMAINE Framework

Abstract page for arXiv paper 2603.04409: Unpacking Human Preference for LLMs: Demographically Aware Evaluation with the HUMAINE Framework

arXiv - AI · 4 min ·
[2603.04406] CTRL-RAG: Contrastive Likelihood Reward Based Reinforcement Learning for Context-Faithful RAG Models
Llms

[2603.04406] CTRL-RAG: Contrastive Likelihood Reward Based Reinforcement Learning for Context-Faithful RAG Models

Abstract page for arXiv paper 2603.04406: CTRL-RAG: Contrastive Likelihood Reward Based Reinforcement Learning for Context-Faithful RAG M...

arXiv - AI · 4 min ·
[2603.04407] Semantic Containment as a Fundamental Property of Emergent Misalignment
Llms

[2603.04407] Semantic Containment as a Fundamental Property of Emergent Misalignment

Abstract page for arXiv paper 2603.04407: Semantic Containment as a Fundamental Property of Emergent Misalignment

arXiv - AI · 3 min ·
[2603.04405] Lost in Translation: How Language Re-Aligns Vision for Cross-Species Pathology
Llms

[2603.04405] Lost in Translation: How Language Re-Aligns Vision for Cross-Species Pathology

Abstract page for arXiv paper 2603.04405: Lost in Translation: How Language Re-Aligns Vision for Cross-Species Pathology

arXiv - Machine Learning · 4 min ·
[2603.05498] The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks
Llms

[2603.05498] The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks

Abstract page for arXiv paper 2603.05498: The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks

arXiv - AI · 3 min ·
[2603.05485] Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation
Llms

[2603.05485] Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation

Abstract page for arXiv paper 2603.05485: Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation

arXiv - AI · 3 min ·
[2603.05399] Judge Reliability Harness: Stress Testing the Reliability of LLM Judges
Llms

[2603.05399] Judge Reliability Harness: Stress Testing the Reliability of LLM Judges

Abstract page for arXiv paper 2603.05399: Judge Reliability Harness: Stress Testing the Reliability of LLM Judges

arXiv - AI · 3 min ·
[2603.05392] Legal interpretation and AI: from expert systems to argumentation and LLMs
Llms

[2603.05392] Legal interpretation and AI: from expert systems to argumentation and LLMs

Abstract page for arXiv paper 2603.05392: Legal interpretation and AI: from expert systems to argumentation and LLMs

arXiv - AI · 3 min ·
[2603.05294] STRUCTUREDAGENT: Planning with AND/OR Trees for Long-Horizon Web Tasks
Llms

[2603.05294] STRUCTUREDAGENT: Planning with AND/OR Trees for Long-Horizon Web Tasks

Abstract page for arXiv paper 2603.05294: STRUCTUREDAGENT: Planning with AND/OR Trees for Long-Horizon Web Tasks

arXiv - AI · 3 min ·
[2603.05290] X-RAY: Mapping LLM Reasoning Capability via Formalized and Calibrated Probes
Llms

[2603.05290] X-RAY: Mapping LLM Reasoning Capability via Formalized and Calibrated Probes

Abstract page for arXiv paper 2603.05290: X-RAY: Mapping LLM Reasoning Capability via Formalized and Calibrated Probes

arXiv - AI · 4 min ·
[2603.05240] GCAgent: Enhancing Group Chat Communication through Dialogue Agents System
Llms

[2603.05240] GCAgent: Enhancing Group Chat Communication through Dialogue Agents System

Abstract page for arXiv paper 2603.05240: GCAgent: Enhancing Group Chat Communication through Dialogue Agents System

arXiv - AI · 3 min ·
[2603.05129] MedCoRAG: Interpretable Hepatology Diagnosis via Hybrid Evidence Retrieval and Multispecialty Consensus
Llms

[2603.05129] MedCoRAG: Interpretable Hepatology Diagnosis via Hybrid Evidence Retrieval and Multispecialty Consensus

Abstract page for arXiv paper 2603.05129: MedCoRAG: Interpretable Hepatology Diagnosis via Hybrid Evidence Retrieval and Multispecialty C...

arXiv - AI · 4 min ·
[2603.05120] Bidirectional Curriculum Generation: A Multi-Agent Framework for Data-Efficient Mathematical Reasoning
Llms

[2603.05120] Bidirectional Curriculum Generation: A Multi-Agent Framework for Data-Efficient Mathematical Reasoning

Abstract page for arXiv paper 2603.05120: Bidirectional Curriculum Generation: A Multi-Agent Framework for Data-Efficient Mathematical Re...

arXiv - AI · 3 min ·
[2603.05044] WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents
Llms

[2603.05044] WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents

Abstract page for arXiv paper 2603.05044: WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents

arXiv - AI · 4 min ·
[2603.05040] Enhancing Zero-shot Commonsense Reasoning by Integrating Visual Knowledge via Machine Imagination
Llms

[2603.05040] Enhancing Zero-shot Commonsense Reasoning by Integrating Visual Knowledge via Machine Imagination

Abstract page for arXiv paper 2603.05040: Enhancing Zero-shot Commonsense Reasoning by Integrating Visual Knowledge via Machine Imagination

arXiv - AI · 3 min ·
[2603.05028] Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure
Llms

[2603.05028] Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure

Abstract page for arXiv paper 2603.05028: Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure

arXiv - AI · 4 min ·
Previous Page 260 Next

Related Topics

Machine Learning Generative AI Natural Language Processing Computer Vision Robotics & Embodied AI AI Safety & Ethics

Stay updated with AI News

Get the latest news, tools, and insights delivered to your inbox.

Subscribe to Newsletter

Daily or weekly digest • Unsubscribe anytime