{"total":104,"rows":[{"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":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121,"area":null},{"id":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105,"area":null},{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92,"area":null},{"id":"2410.13640","title":"Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation","created":"2024-10-17","cited_by_count":57,"area":null},{"id":"2503.14477","title":"Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations","created":"2025-03-18","cited_by_count":48,"area":null},{"id":"2402.10426","title":"DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection","created":"2024-02-16","cited_by_count":41,"area":null},{"id":"2412.12472","title":"Knowledge Boundary of Large Language Models: A Survey","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2502.04506","title":"When One LLM Drools, Multi-LLM Collaboration Rules","created":"2025-02-06","cited_by_count":28,"area":null},{"id":"2410.11163","title":"Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2502.12964","title":"Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer","created":"2025-02-18","cited_by_count":27,"area":null},{"id":"2509.25760","title":"TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning","created":"2025-09-30","cited_by_count":27,"area":null},{"id":"2406.11278","title":"Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs","created":"2024-06-17","cited_by_count":23,"area":null},{"id":"2502.04510","title":"Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems","created":"2025-02-06","cited_by_count":23,"area":null},{"id":"2407.12858","title":"Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)","created":"2024-07-10","cited_by_count":20,"area":null},{"id":"2502.19110","title":"Conformal Linguistic Calibration: Trading-off between Factuality and Specificity","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2502.14427","title":"Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models","created":"2025-02-20","cited_by_count":18,"area":null},{"id":"2406.11514","title":"Counterfactual Debating with Preset Stances for Hallucination Elimination of LLMs","created":"2024-06-17","cited_by_count":17,"area":null},{"id":"2406.15948","title":"Teaching LLMs to Abstain across Languages via Multilingual Feedback","created":"2024-06-22","cited_by_count":14,"area":null},{"id":"2410.22071","title":"Distinguishing Ignorance from Error in LLM Hallucinations","created":"2024-10-29","cited_by_count":14,"area":null},{"id":"2412.06748","title":"Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models","created":"2024-12-09","cited_by_count":14,"area":null},{"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":"2410.15512","title":"Reverse Question Answering: Can an LLM Write a Question so Hard (or Bad) that it Can't Answer?","created":"2024-10-20","cited_by_count":13,"area":null},{"id":"2509.22449","title":"Detecting (Un)answerability in Large Language Models with Linear Directions","created":"2025-09-26","cited_by_count":13,"area":null},{"id":"2404.06283","title":"LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements","created":"2024-04-09","cited_by_count":12,"area":null},{"id":"2406.10173","title":"IntentionQA: A Benchmark for Evaluating Purchase Intention Comprehension Abilities of Language Models in E-commerce","created":"2024-06-14","cited_by_count":11,"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":"2509.08269","title":"A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving","created":"2025-09-10","cited_by_count":11,"area":null},{"id":"2510.12040","title":"Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions","created":"2025-10-14","cited_by_count":11,"area":null},{"id":"2601.05503","title":"Over-Searching in Search-Augmented Large Language Models","created":"2026-01-09","cited_by_count":11,"area":null},{"id":"2512.24661","title":"Do Large Language Models Know What They Are Capable Of?","created":"2025-12-31","cited_by_count":10,"area":null},{"id":"2406.14721","title":"1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators?","created":"2024-06-20","cited_by_count":9,"area":null},{"id":"2410.14545","title":"Tell me what I need to know: Exploring LLM-based (Personalized) Abstractive Multi-Source Meeting Summarization","created":"2024-10-18","cited_by_count":9,"area":null},{"id":"2412.12527","title":"When to Speak, When to Abstain: Contrastive Decoding with Abstention","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2412.12767","title":"A Survey of Calibration Process for Black-Box LLMs","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2505.21701","title":"Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2510.15232","title":"FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domain","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2410.02499","title":"Defining Knowledge: Bridging Epistemology and Large Language Models","created":"2024-10-03","cited_by_count":7,"area":null},{"id":"2602.04755","title":"When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?","created":"2026-02-04","cited_by_count":7,"area":null},{"id":"2503.01332","title":"Answer, Refuse, or Guess? Investigating Risk-Aware Decision Making in Language Models","created":"2025-03-03","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":"2510.24222","title":"HACK: Hallucinations Along Certainty and Knowledge Axes","created":"2025-10-28","cited_by_count":6,"area":null},{"id":"2601.21257","title":"MoCo: A One-Stop Shop for Model Collaboration Research","created":"2026-01-29","cited_by_count":6,"area":null},{"id":"2410.14748","title":"ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries","created":"2024-10-17","cited_by_count":5,"area":null},{"id":"2412.04606","title":"Semantic Consistency-Based Uncertainty Quantification for Factuality in Radiology Report Generation","created":"2024-12-05","cited_by_count":5,"area":null},{"id":"2504.14375","title":"Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Prompts","created":"2025-04-19","cited_by_count":5,"area":null},{"id":"2408.05873","title":"Recognizing Limits: Investigating Infeasibility in Large Language Models","created":"2024-08-11","cited_by_count":4,"area":null},{"id":"2409.14037","title":"Can LLMs replace Neil deGrasse Tyson? Evaluating the Reliability of LLMs as Science Communicators","created":"2024-09-21","cited_by_count":4,"area":null},{"id":"2410.14405","title":"Fact Recall, Heuristics or Pure Guesswork? Precise Interpretations of Language Models for Fact Completion","created":"2024-10-18","cited_by_count":4,"area":null},{"id":"2504.11381","title":"RankAlign: A Ranking View of the Generator-Validator Gap in Large Language Models","created":"2025-04-15","cited_by_count":4,"area":null},{"id":"2504.18346","title":"Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review","created":"2025-04-25","cited_by_count":4,"area":null},{"id":"2505.16518","title":"CUB: Benchmarking Context Utilisation Techniques for Language Models","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2505.24302","title":"ScienceMeter: Tracking Scientific Knowledge Updates in Language Models","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2507.08203","title":"TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2604.25591","title":"Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models","created":"2026-04-28","cited_by_count":4,"area":null},{"id":"2605.15000","title":"Quantifying and Mitigating Premature Closure in Frontier LLMs","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2605.15156","title":"MeMo: Memory as a Model","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2505.20487","title":"InFact: Informativeness Alignment for Improved LLM Factuality","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2506.00694","title":"Measuring Faithfulness and Abstention: An Automated Pipeline for Evaluating LLM-Generated 3-ply Case-Based Legal Arguments","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2510.03930","title":"LLM Chemistry Estimation for Multi-LLM Recommendation","created":"2025-10-04","cited_by_count":3,"area":null},{"id":"2511.03166","title":"Measuring Aleatoric and Epistemic Uncertainty in LLMs: Empirical Evaluation on ID and OOD QA Tasks","created":"2025-11-05","cited_by_count":3,"area":null},{"id":"2604.25149","title":"Semantic Layers for Reliable LLM-Powered Data Analytics: A Paired Benchmark of Accuracy and Hallucination Across Three Frontier Models","created":"2026-04-28","cited_by_count":3,"area":null},{"id":"2412.07430","title":"Knowledge Graph Guided Evaluation of Abstention Techniques","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2501.05981","title":"Hermit Kingdom Through the Lens of Multiple Perspectives: A Case Study of LLM Hallucination on North Korea","created":"2025-01-10","cited_by_count":2,"area":null},{"id":"2503.14797","title":"FACTS&EVIDENCE: An Interactive Tool for Transparent Fine-Grained Factual Verification of Machine-Generated Text","created":"2025-03-19","cited_by_count":2,"area":null},{"id":"2503.23687","title":"MKA: Leveraging Cross-Lingual Consensus for Model Abstention","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2505.16648","title":"Collaboration among Multiple Large Language Models for Medical Question Answering","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2506.03476","title":"Delta-KNN: Improving Demonstration Selection in In-Context Learning for Alzheimer's Disease Detection","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2506.04051","title":"High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2509.15356","title":"Predicting Language Models' Success at Zero-Shot Probabilistic Prediction","created":"2025-09-18","cited_by_count":2,"area":null},{"id":"2602.11908","title":"When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation","created":"2026-02-12","cited_by_count":2,"area":null},{"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":"2502.13648","title":"UniKnow: A Unified Framework for Reliable Language Model Behavior across Parametric and External Knowledge","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2503.12556","title":"From Guessing to Asking: An Approach to Resolving the Persona Knowledge Gap in LLMs during Multi-Turn Conversations","created":"2025-03-16","cited_by_count":1,"area":null},{"id":"2505.19430","title":"Deriving Strategic Market Insights with Large Language Models: A Benchmark for Forward Counterfactual Generation","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2505.20921","title":"Automatic Transmission for LLM Tiers: Optimizing Cost and Accuracy in Large Language Models","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2511.01188","title":"ZoFia: Zero-Shot Fake News Detection with Entity-Guided Retrieval and Multi-LLM Interaction","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2512.03025","title":"LORE: A Large Generative Model for Search Relevance","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2604.13201","title":"InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2605.05626","title":"When2Speak: A Dataset for Temporal Participation and Turn-Taking in Multi-Party Conversations for Large Language Models","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2607.03739","title":"A Failure-Mode Benchmark for Polymorphic Sybil Poisoning in RAG","created":"2026-07-04","cited_by_count":1,"area":null},{"id":"2609.01352","title":"CHARM: Character Hallucination for Multicultural Role Play Benchmark","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2407.00191","title":"MetaKP: On-Demand Keyphrase Generation","created":"2024-06-28","cited_by_count":0,"area":null},{"id":"2508.13754","title":"Expertise-aware Multi-LLM Recruitment and Collaboration for Medical Decision-Making","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2508.15139","title":"Identifying and Answering Questions with False Assumptions: An Interpretable Approach","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2509.05899","title":"X-SQL: Expert Schema Linking and Understanding of Text-to-SQL with Multi-LLMs","created":"2025-09-07","cited_by_count":0,"area":null},{"id":"2510.03527","title":"Sample, Align, Synthesize: Graph-Based Response Synthesis with ConGrs","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2512.06227","title":"Automated Data Enrichment using Confidence-Aware Fine-Grained Debate among Open-Source LLMs for Mental Health and Online Safety","created":"2025-12-06","cited_by_count":0,"area":null},{"id":"2602.10801","title":"Deep Learning-based Method for Expressing Knowledge Boundary of Black-Box LLM","created":"2026-02-11","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":"2605.30481","title":"When English Rewrites Local Knowledge: Global Narrative Dominance in Large Language Models","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.02289","title":"DECK: A Consistency x Confidence Taxonomy of LLM Hallucinations","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.17904","title":"DiagFlowBench: Evaluating How Language Models Handle Off-Procedure Inputs in Grounded Diagnostic Dialogue","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.27382","title":"AI-Model Network: Concept, Current State and Future","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2607.12831","title":"Knowledgeless Language Models: Suppressing Parametric Recall for Evidence-Grounded Language Modeling","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.18496","title":"Semi-Automated Detection of Gaps in LLM Security Knowledge","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.14683","title":"One Score, Two Decisions: Selective Prediction on the Rare-Disease Tail","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.25325","title":"FinRiskAtlas: Decision-Aligned Evaluation of Large Language Models for Financial Risk Review","created":"2026-08-26","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":"2609.04362","title":"Knowing When Not to Answer: Pseudo-Ensembles for Abstention in Music Audio-Language Models","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":"100"}