{"total":288,"rows":[{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698,"area":null},{"id":"2404.10774","title":"MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents","created":"2024-04-16","cited_by_count":257,"area":"rag"},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2311.13614","title":"HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data","created":"2023-11-22","cited_by_count":126,"area":"mllm"},{"id":"2406.15627","title":"Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph","created":"2024-06-21","cited_by_count":105,"area":null},{"id":"2407.18370","title":"Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement","created":"2024-07-25","cited_by_count":105,"area":null},{"id":"2402.15570","title":"Fast Adversarial Attacks on Language Models In One GPU Minute","created":"2024-02-23","cited_by_count":88,"area":"safety"},{"id":"2407.01370","title":"Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems","created":"2024-07-01","cited_by_count":87,"area":"rag"},{"id":"2407.04069","title":"A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations","created":"2024-07-04","cited_by_count":85,"area":null},{"id":"2405.10825","title":"Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities","created":"2024-05-17","cited_by_count":83,"area":"lr"},{"id":"2402.13249","title":"TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization","created":"2024-02-20","cited_by_count":66,"area":null},{"id":"2411.09523","title":"Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents","created":"2024-11-14","cited_by_count":65,"area":"agents"},{"id":"2502.12289","title":"Evaluating Step-by-step Reasoning Traces: A Survey","created":"2025-02-17","cited_by_count":63,"area":"lr"},{"id":"2406.20079","title":"Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification","created":"2024-06-28","cited_by_count":44,"area":null},{"id":"2409.07394","title":"AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge","created":"2024-09-11","cited_by_count":37,"area":null},{"id":"2411.02400","title":"Decomposition Dilemmas: Does Claim Decomposition Boost or Burden Fact-Checking Performance?","created":"2024-10-17","cited_by_count":36,"area":null},{"id":"2310.03951","title":"Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations","created":"2023-10-06","cited_by_count":35,"area":null},{"id":"2311.01463","title":"Creating Trustworthy LLMs: Dealing with Hallucinations in Healthcare AI","created":"2023-09-26","cited_by_count":33,"area":null},{"id":"2409.15277","title":"A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?","created":"2024-09-23","cited_by_count":33,"area":null},{"id":"2307.12966","title":"Aligning Large Language Models with Human: A Survey","created":"2023-07-24","cited_by_count":32,"area":"alignment"},{"id":"2507.16488","title":"ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs","created":"2025-07-22","cited_by_count":32,"area":null},{"id":"2410.03775","title":"Beyond correlation: The Impact of Human Uncertainty in Measuring the Effectiveness of Automatic Evaluation and LLM-as-a-Judge","created":"2024-10-03","cited_by_count":31,"area":null},{"id":"2407.06863","title":"Beyond Aesthetics: Cultural Competence in Text-to-Image Models","created":"2024-07-09","cited_by_count":30,"area":null},{"id":"2502.04964","title":"Uncertainty Quantification for LLMs through Minimum Bayes Risk: Bridging Confidence and Consistency","created":"2025-02-07","cited_by_count":30,"area":null},{"id":"2403.02270","title":"FENICE: Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction","created":"2024-03-04","cited_by_count":28,"area":null},{"id":"2407.02397","title":"Learning to Refine with Fine-Grained Natural Language Feedback","created":"2024-07-02","cited_by_count":27,"area":null},{"id":"2405.14486","title":"RefChecker: Reference-based Fine-grained Hallucination Checker and Benchmark for Large Language Models","created":"2024-05-23","cited_by_count":25,"area":null},{"id":"2412.06771","title":"Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty","created":"2024-12-09","cited_by_count":25,"area":null},{"id":"2408.14317","title":"Claim Verification in the Age of Large Language Models: A Survey","created":"2024-08-26","cited_by_count":24,"area":null},{"id":"2410.13210","title":"FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs","created":"2024-10-17","cited_by_count":24,"area":"rag"},{"id":"2405.13179","title":"RAG-RLRC-LaySum at BioLaySumm: Integrating Retrieval-Augmented Generation and Readability Control for Layman Summarization of Biomedical Texts","created":"2024-05-21","cited_by_count":23,"area":"rag"},{"id":"2405.18027","title":"TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models","created":"2024-05-28","cited_by_count":22,"area":null},{"id":"2410.23609","title":"On Positional Bias of Faithfulness for Long-form Summarization","created":"2024-10-31","cited_by_count":22,"area":null},{"id":"2502.13668","title":"PeerQA: A Scientific Question Answering Dataset from Peer Reviews","created":"2025-02-19","cited_by_count":22,"area":null},{"id":"2508.08285","title":"The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs","created":"2025-08-01","cited_by_count":22,"area":null},{"id":"2401.08358","title":"Hallucination Detection and Hallucination Mitigation: An Investigation","created":"2024-01-16","cited_by_count":21,"area":null},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21,"area":"alignment"},{"id":"2504.13677","title":"Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results","created":"2025-04-18","cited_by_count":21,"area":null},{"id":"2408.09169","title":"Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices","created":"2024-08-17","cited_by_count":20,"area":null},{"id":"2409.16603","title":"Overview of the First Shared Task on Clinical Text Generation: RRG24 and \"Discharge Me!\"","created":"2024-09-25","cited_by_count":20,"area":null},{"id":"2410.18889","title":"Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance","created":"2024-10-24","cited_by_count":20,"area":null},{"id":"2505.04847","title":"Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards","created":"2025-05-07","cited_by_count":20,"area":"rag"},{"id":"2403.01061","title":"Reading Subtext: Evaluating Large Language Models on Short Story Summarization with Writers","created":"2024-03-02","cited_by_count":19,"area":null},{"id":"2410.22954","title":"Retrieval-Augmented Generation with Estimation of Source Reliability","created":"2024-10-30","cited_by_count":19,"area":"rag"},{"id":"2402.11456","title":"FactPICO: Factuality Evaluation for Plain Language Summarization of Medical Evidence","created":"2024-02-18","cited_by_count":18,"area":null},{"id":"2404.04251","title":"Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2)","created":"2024-04-05","cited_by_count":18,"area":null},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2406.13779","title":"FoRAG: Factuality-optimized Retrieval Augmented Generation for Web-enhanced Long-form Question Answering","created":"2024-06-19","cited_by_count":18,"area":"rag"},{"id":"2408.08566","title":"Overview of the BioLaySumm 2024 Shared Task on the Lay Summarization of Biomedical Research Articles","created":"2024-08-16","cited_by_count":18,"area":null},{"id":"2410.04068","title":"ECon: On the Detection and Resolution of Evidence Conflicts","created":"2024-10-05","cited_by_count":18,"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":"2502.15799","title":"Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models","created":"2025-02-18","cited_by_count":18,"area":"lr"},{"id":"2506.01859","title":"CONFETTI: Conversational Function-Calling Evaluation Through Turn-Level Interactions","created":"2025-06-02","cited_by_count":18,"area":"agents"},{"id":"2403.16527","title":"Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art","created":"2024-03-25","cited_by_count":17,"area":null},{"id":"2406.15264","title":"Towards Fine-Grained Citation Evaluation in Generated Text: A Comparative Analysis of Faithfulness Metrics","created":"2024-06-21","cited_by_count":17,"area":"rag"},{"id":"2410.19155","title":"Lived Experience Not Found: LLMs Struggle to Align with Experts on Addressing Adverse Drug Reactions from Psychiatric Medication Use","created":"2024-10-24","cited_by_count":17,"area":null},{"id":"2411.04424","title":"Bayesian Calibration of Win Rate Estimation with LLM Evaluators","created":"2024-11-07","cited_by_count":16,"area":null},{"id":"2505.20045","title":"Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads","created":"2025-05-26","cited_by_count":16,"area":null},{"id":"2404.11184","title":"FIZZ: Factual Inconsistency Detection by Zoom-in Summary and Zoom-out Document","created":"2024-04-17","cited_by_count":15,"area":null},{"id":"2407.01942","title":"Certainly Uncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness","created":"2024-07-02","cited_by_count":14,"area":null},{"id":"2409.03708","title":"RAG based Question-Answering for Contextual Response Prediction System","created":"2024-09-05","cited_by_count":14,"area":null},{"id":"2501.17144","title":"FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop Data","created":"2025-01-28","cited_by_count":14,"area":null},{"id":"2406.13124","title":"Learning to Generate Answers with Citations via Factual Consistency Models","created":"2024-06-19","cited_by_count":13,"area":null},{"id":"2407.21057","title":"Multi-group Uncertainty Quantification for Long-form Text Generation","created":"2024-07-25","cited_by_count":13,"area":null},{"id":"2410.03198","title":"PersoBench: Benchmarking Personalized Response Generation in Large Language Models","created":"2024-10-04","cited_by_count":13,"area":null},{"id":"2504.00939","title":"WikiVideo: Article Generation from Multiple Videos","created":"2025-04-01","cited_by_count":13,"area":"rag"},{"id":"2506.04156","title":"A Dataset for Addressing Patient's Information Needs related to Clinical Course of Hospitalization","created":"2025-06-04","cited_by_count":13,"area":null},{"id":"2312.02554","title":"ULMA: Unified Language Model Alignment with Human Demonstration and Point-wise Preference","created":"2023-12-05","cited_by_count":12,"area":"alignment"},{"id":"2312.08800","title":"Evaluating Large Language Models for Health-related Queries with Presuppositions","created":"2023-12-14","cited_by_count":12,"area":null},{"id":"2402.14558","title":"LLMs with Industrial Lens: Deciphering the Challenges and Prospects -- A Survey","created":"2024-02-22","cited_by_count":12,"area":null},{"id":"2404.03745","title":"Fakes of Varying Shades: How Warning Affects Human Perception and Engagement Regarding LLM Hallucinations","created":"2024-04-04","cited_by_count":12,"area":null},{"id":"2409.20246","title":"Analysing Zero-Shot Readability-Controlled Sentence Simplification","created":"2024-09-30","cited_by_count":12,"area":null},{"id":"2410.23703","title":"OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models","created":"2024-10-31","cited_by_count":12,"area":"lr"},{"id":"2502.16514","title":"GraphCheck: Breaking Long-Term Text Barriers with Extracted Knowledge Graph-Powered Fact-Checking","created":"2025-02-23","cited_by_count":12,"area":null},{"id":"2311.09521","title":"AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation","created":"2023-11-16","cited_by_count":11,"area":null},{"id":"2411.16638","title":"Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation","created":"2024-11-25","cited_by_count":11,"area":null},{"id":"2506.00549","title":"Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages","created":"2025-05-31","cited_by_count":11,"area":null},{"id":"2509.19333","title":"Pluralistic Off-policy Evaluation and Alignment","created":"2025-09-15","cited_by_count":11,"area":"alignment"},{"id":"2407.01080","title":"Face4RAG: Factual Consistency Evaluation for Retrieval Augmented Generation in Chinese","created":"2024-07-01","cited_by_count":10,"area":"rag"},{"id":"2506.12937","title":"HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance","created":"2025-06-15","cited_by_count":10,"area":"lr"},{"id":"2508.17670","title":"CoCoA: Confidence and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Models","created":"2025-08-25","cited_by_count":10,"area":null},{"id":"2403.00067","title":"Query-OPT: Optimizing Inference of Large Language Models via Multi-Query Instructions in Meeting Summarization","created":"2024-02-29","cited_by_count":9,"area":null},{"id":"2407.06501","title":"STORYSUMM: Evaluating Faithfulness in Story Summarization","created":"2024-07-09","cited_by_count":9,"area":null},{"id":"2408.10692","title":"Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models","created":"2024-08-20","cited_by_count":9,"area":null},{"id":"2410.11315","title":"SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation","created":"2024-10-15","cited_by_count":9,"area":"rag"},{"id":"2502.00977","title":"Context-Aware Hierarchical Merging for Long Document Summarization","created":"2025-02-03","cited_by_count":9,"area":null},{"id":"2503.15272","title":"MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaboration","created":"2025-03-19","cited_by_count":9,"area":"agents"},{"id":"2507.06196","title":"UQLM: A Python Package for Uncertainty Quantification in Large Language Models","created":"2025-07-08","cited_by_count":9,"area":null},{"id":"2307.02729","title":"Text Alignment Is An Efficient Unified Model for Massive NLP Tasks","created":"2023-07-06","cited_by_count":8,"area":null},{"id":"2402.16315","title":"Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models","created":"2024-02-26","cited_by_count":8,"area":"mllm"},{"id":"2405.00711","title":"Fake Artificial Intelligence Generated Contents (FAIGC): A Survey of Theories, Detection Methods, and Opportunities","created":"2024-04-25","cited_by_count":8,"area":"diffusion"},{"id":"2411.19655","title":"Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-Oasis","created":"2024-11-29","cited_by_count":8,"area":null},{"id":"2412.07096","title":"QAPyramid: Fine-grained Evaluation of Content Selection for Text Summarization","created":"2024-12-10","cited_by_count":8,"area":null},{"id":"2502.06185","title":"Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarization","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2502.15419","title":"Beyond Translation: LLM-Based Data Generation for Multilingual Fact-Checking","created":"2025-02-21","cited_by_count":8,"area":null},{"id":"2505.11095","title":"Towards Better Evaluation for Generated Patent Claims","created":"2025-05-16","cited_by_count":8,"area":null},{"id":"2510.00280","title":"ReEvalMed: Rethinking Medical Report Evaluation by Aligning Metrics with Real-World Clinical Judgment","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2404.12041","title":"A Survey of Automatic Hallucination Evaluation on Natural Language Generation","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2409.18618","title":"Model-based Preference Optimization in Abstractive Summarization without Human Feedback","created":"2024-09-27","cited_by_count":7,"area":"alignment"},{"id":"2410.13456","title":"Unlocking Legal Knowledge: A Multilingual Dataset for Judicial Summarization in Switzerland","created":"2024-10-17","cited_by_count":7,"area":null}],"next_cursor":"100"}