{"total":74,"rows":[{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2402.10978","title":"Language Models with Conformal Factuality Guarantees","created":"2024-02-15","cited_by_count":131,"area":null},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2403.05612","title":"Unfamiliar Finetuning Examples Control How Language Models Hallucinate","created":"2024-03-08","cited_by_count":87,"area":"alignment"},{"id":"2503.03750","title":"The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems","created":"2025-03-05","cited_by_count":72,"area":"agents"},{"id":"2403.18349","title":"Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback","created":"2024-03-27","cited_by_count":66,"area":"alignment"},{"id":"2402.05391","title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","created":"2024-02-08","cited_by_count":53,"area":null},{"id":"2503.02623","title":"Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Models","created":"2025-03-04","cited_by_count":52,"area":null},{"id":"2509.03730","title":"The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs","created":"2025-09-03","cited_by_count":36,"area":null},{"id":"2402.16048","title":"How Likely Do LLMs with CoT Mimic Human Reasoning?","created":"2024-02-25","cited_by_count":34,"area":"lr"},{"id":"2408.11865","title":"How Susceptible are LLMs to Influence in Prompts?","created":"2024-08-17","cited_by_count":33,"area":null},{"id":"2509.25760","title":"TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning","created":"2025-09-30","cited_by_count":27,"area":null},{"id":"2406.13261","title":"BeHonest: Benchmarking Honesty in Large Language Models","created":"2024-06-19","cited_by_count":24,"area":null},{"id":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23,"area":null},{"id":"2408.09773","title":"Are Large Language Models More Honest in Their Probabilistic or Verbalized Confidence?","created":"2024-08-19","cited_by_count":23,"area":null},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"area":"alignment"},{"id":"2401.17882","title":"I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBench","created":"2024-01-31","cited_by_count":21,"area":"lr"},{"id":"2405.14383","title":"Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answering","created":"2024-05-23","cited_by_count":20,"area":null},{"id":"2402.01909","title":"On Catastrophic Inheritance of Large Foundation Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2606.28733","title":"Agentic Abstention: Do Agents Know When to Stop Instead of Act?","created":"2026-06-27","cited_by_count":15,"area":"agents"},{"id":"2503.14481","title":"Don't lie to your friends: Learning what you know from collaborative self-play","created":"2025-03-18","cited_by_count":14,"area":null},{"id":"2404.03862","title":"Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data","created":"2024-04-05","cited_by_count":13,"area":"alignment"},{"id":"2407.21057","title":"Multi-group Uncertainty Quantification for Long-form Text Generation","created":"2024-07-25","cited_by_count":13,"area":null},{"id":"2410.17234","title":"Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy","created":"2024-10-22","cited_by_count":11,"area":null},{"id":"2505.23224","title":"MMBoundary: Advancing MLLM Knowledge Boundary Awareness through Reasoning Step Confidence Calibration","created":"2025-05-29","cited_by_count":11,"area":"lr"},{"id":"2410.06913","title":"Utilize the Flow before Stepping into the Same River Twice: Certainty Represented Knowledge Flow for Refusal-Aware Instruction Tuning","created":"2024-10-09","cited_by_count":10,"area":"safety"},{"id":"2506.00519","title":"CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention","created":"2025-05-31","cited_by_count":10,"area":"lr"},{"id":"2410.11055","title":"Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only","created":"2024-10-14","cited_by_count":9,"area":"alignment"},{"id":"2505.19387","title":"Alignment of large language models with constrained learning","created":"2025-05-26","cited_by_count":8,"area":"alignment"},{"id":"2509.20175","title":"Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AI","created":"2025-09-24","cited_by_count":7,"area":"agents"},{"id":"2406.05055","title":"VCSearch: Bridging the Gap Between Well-Defined and Ill-Defined Problems in Mathematical Reasoning","created":"2024-06-07","cited_by_count":6,"area":"lr"},{"id":"2501.01336","title":"Aligning Large Language Models for Faithful Integrity Against Opposing Argument","created":"2025-01-02","cited_by_count":6,"area":"alignment"},{"id":"2505.16170","title":"When Do LLMs Admit Their Mistakes? Understanding The Role Of Model Belief In Retraction","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2507.04976","title":"Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models","created":"2025-07-07","cited_by_count":6,"area":"mllm"},{"id":"2509.23782","title":"Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2510.01152","title":"MASH: Modeling Abstention via Selective Help-Seeking","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2505.07184","title":"Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs","created":"2025-05-12","cited_by_count":5,"area":"agents"},{"id":"2605.01428","title":"Hallucinations Undermine Trust; Metacognition is a Way Forward","created":"2026-05-02","cited_by_count":5,"area":null},{"id":"2504.09895","title":"Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data","created":"2025-04-14","cited_by_count":4,"area":"alignment"},{"id":"2507.08371","title":"The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality","created":"2025-07-11","cited_by_count":4,"area":"synth"},{"id":"2606.32032","title":"Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs","created":"2026-06-30","cited_by_count":4,"area":"alignment"},{"id":"2406.01931","title":"Dishonesty in Helpful and Harmless Alignment","created":"2024-06-04","cited_by_count":3,"area":"alignment"},{"id":"2409.16913","title":"Tell Me What You Don't Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2506.14387","title":"SEAT: Sparse Entity-Aware Tuning for Knowledge Adaptation while Preserving Epistemic Abstention","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2507.06489","title":"On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks","created":"2025-07-09","cited_by_count":3,"area":null},{"id":"2509.17380","title":"Correlation or Causation: Analyzing the Causal Structures of LLM and LRM Reasoning Process","created":"2025-09-22","cited_by_count":3,"area":"lr"},{"id":"2510.17509","title":"Annotation-Efficient Universal Honesty Alignment","created":"2025-10-20","cited_by_count":3,"area":null},{"id":"2602.20696","title":"PromptCD: Test-Time Behavior Enhancement via Polarity-Prompt Contrastive Decoding","created":"2026-02-24","cited_by_count":3,"area":null},{"id":"2607.01612","title":"Scaling with Confidence: Calibrating Confidence of LLMs for Adaptive Test Time Scaling","created":"2026-07-02","cited_by_count":3,"area":"lr"},{"id":"2502.12767","title":"R2-KG: General-Purpose Dual-Agent Framework for Reliable Reasoning on Knowledge Graphs","created":"2025-02-18","cited_by_count":2,"area":"lr"},{"id":"2505.12182","title":"Truth Neurons","created":"2025-05-18","cited_by_count":2,"area":null},{"id":"2505.13545","title":"Know Or Not: a library for evaluating out-of-knowledge base robustness","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2602.13571","title":"LLM-Confidence Reranker: A Training-Free Approach for Enhancing Retrieval-Augmented Generation Systems","created":"2026-02-14","cited_by_count":2,"area":"rag"},{"id":"2608.26372","title":"Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2609.07879","title":"Do Large Language Models Know What They Don't Know II? A Fully Behavioral, Non-Cognitive Measure of Epistemic Honesty","created":"2026-09-07","cited_by_count":2,"area":null},{"id":"2412.11196","title":"Drawing the Line: Enhancing Trustworthiness of MLLMs Through the Power of Refusal","created":"2024-12-15","cited_by_count":1,"area":"mllm"},{"id":"2606.00251","title":"Capability Self-Assessment in Large Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2410.06225","title":"A Timeline and Analysis for Representation Plasticity in Large Language Models","created":"2024-10-08","cited_by_count":0,"area":"mechinterp"},{"id":"2505.17636","title":"Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2508.06592","title":"Towards Integrated Alignment","created":"2025-08-08","cited_by_count":0,"area":"alignment"},{"id":"2509.13702","title":"DSCC-HS: A Dynamic Self-Reinforcing Framework for Hallucination Suppression in Large Language Models","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2512.08944","title":"Enhancing Reliability across Short and Long-Form QA via Reinforcement Learning","created":"2025-11-19","cited_by_count":0,"area":"lr"},{"id":"2601.01156","title":"DHI: Leveraging Diverse Hallucination Induction for Enhanced Contrastive Factuality Control in Large Language Models","created":"2026-01-03","cited_by_count":0,"area":null},{"id":"2605.10391","title":"Phoenix-VL 1.5 Medium Technical Report","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.17029","title":"Task Abstention for Large Language Models in Code Generation","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.01581","title":"Agent System Operations: Categorization, Challenges, and Future Directions","created":"2026-06-01","cited_by_count":0,"area":"lr"},{"id":"2607.27637","title":"MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models","created":"2026-07-30","cited_by_count":0,"area":"mllm"},{"id":"2608.26168","title":"Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2609.02771","title":"From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.33721","title":"Shared Experience, Separate Learning: Companion Confidence Calibration for LLMs","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.38909","title":"Unlearning Deceptive Behaviors in LLMs with Contrastive Forget Sets","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2610.03190","title":"Not Until the Evidence Says So: Teaching LLM Investigators When to Close a Case","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.16318","title":"Strong yet Controllable LLM Abstention without Learning to Abstain","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}