{"total":179,"rows":[{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601,"area":null},{"id":"2401.11817","title":"Hallucination is Inevitable: An Innate Limitation of Large Language Models","created":"2024-01-22","cited_by_count":332,"area":null},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"id":"2401.01313","title":"A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models","created":"2024-01-02","cited_by_count":269,"area":null},{"id":"2403.10131","title":"RAFT: Adapting Language Model to Domain Specific RAG","created":"2024-03-15","cited_by_count":262,"area":null},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206,"area":null},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"area":null},{"id":"2504.07952","title":"Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory","created":"2025-04-10","cited_by_count":163,"area":null},{"id":"2504.19314","title":"BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese","created":"2025-04-27","cited_by_count":145,"area":null},{"id":"2406.19276","title":"VERISCORE: Evaluating the factuality of verifiable claims in long-form text generation","created":"2024-06-27","cited_by_count":117,"area":null},{"id":"2311.14648","title":"Calibrated Language Models Must Hallucinate","created":"2023-11-24","cited_by_count":115,"area":null},{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92,"area":null},{"id":"2404.14851","title":"From Matching to Generation: A Survey on Generative Information Retrieval","created":"2024-04-23","cited_by_count":89,"area":null},{"id":"2311.09000","title":"Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers","created":"2023-11-15","cited_by_count":87,"area":null},{"id":"2312.15710","title":"Alleviating Hallucinations of Large Language Models through Induced Hallucinations","created":"2023-12-25","cited_by_count":79,"area":null},{"id":"2407.10817","title":"Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation","created":"2024-07-15","cited_by_count":74,"area":null},{"id":"2402.02420","title":"Factuality of Large Language Models: A Survey","created":"2024-02-04","cited_by_count":66,"area":null},{"id":"2407.00128","title":"When Search Engine Services meet Large Language Models: Visions and Challenges","created":"2024-06-28","cited_by_count":59,"area":null},{"id":"2509.07968","title":"SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge","created":"2025-09-09","cited_by_count":54,"area":null},{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2402.02713","title":"Position: What Can Large Language Models Tell Us about Time Series Analysis","created":"2024-02-05","cited_by_count":47,"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":"2311.09114","title":"Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectification","created":"2023-11-15","cited_by_count":38,"area":null},{"id":"2506.06541","title":"KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes","created":"2025-06-06","cited_by_count":33,"area":null},{"id":"2311.09731","title":"Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge","created":"2023-11-16","cited_by_count":32,"area":null},{"id":"2505.14963","title":"MedBrowseComp: Benchmarking Medical Deep Research and Computer Use","created":"2025-05-20","cited_by_count":30,"area":null},{"id":"2311.05876","title":"Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications","created":"2023-11-10","cited_by_count":28,"area":null},{"id":"2408.11832","title":"OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs","created":"2024-08-06","cited_by_count":28,"area":null},{"id":"2411.13154","title":"DMQR-RAG: Diverse Multi-Query Rewriting for RAG","created":"2024-11-20","cited_by_count":27,"area":null},{"id":"2405.08460","title":"Is Your LLM Outdated? A Deep Look at Temporal Generalization","created":"2024-05-14","cited_by_count":26,"area":null},{"id":"2405.16089","title":"Towards Completeness-Oriented Tool Retrieval for Large Language Models","created":"2024-05-25","cited_by_count":26,"area":null},{"id":"2503.05683","title":"WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs","created":"2025-03-07","cited_by_count":26,"area":null},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2402.16797","title":"Set the Clock: Temporal Alignment of Pretrained Language Models","created":"2024-02-26","cited_by_count":25,"area":null},{"id":"2401.17585","title":"Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks","created":"2024-01-31","cited_by_count":24,"area":null},{"id":"2502.15844","title":"Hallucination Detection in Large Language Models with Metamorphic Relations","created":"2025-02-20","cited_by_count":24,"area":null},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2402.11100","title":"When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models","created":"2024-02-16","cited_by_count":22,"area":null},{"id":"2402.19248","title":"Let LLMs Take on the Latest Challenges! A Chinese Dynamic Question Answering Benchmark","created":"2024-02-29","cited_by_count":22,"area":null},{"id":"2402.12261","title":"NEO-BENCH: Evaluating Robustness of Large Language Models with Neologisms","created":"2024-02-19","cited_by_count":20,"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":"2412.17032","title":"MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge","created":"2024-12-22","cited_by_count":20,"area":null},{"id":"2411.08324","title":"Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle","created":"2024-11-13","cited_by_count":19,"area":null},{"id":"2406.06326","title":"Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching","created":"2024-06-10","cited_by_count":17,"area":null},{"id":"2407.03525","title":"UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization","created":"2024-07-03","cited_by_count":17,"area":null},{"id":"2410.13961","title":"From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization","created":"2024-10-17","cited_by_count":17,"area":null},{"id":"2512.10791","title":"The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality","created":"2025-12-11","cited_by_count":17,"area":null},{"id":"2406.10099","title":"Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuning","created":"2024-06-14","cited_by_count":16,"area":null},{"id":"2402.11034","title":"PAT-Questions: A Self-Updating Benchmark for Present-Anchored Temporal Question-Answering","created":"2024-02-16","cited_by_count":15,"area":null},{"id":"2408.13808","title":"Towards Reliable Medical Question Answering: Techniques and Challenges in Mitigating Hallucinations in Language Models","created":"2024-08-25","cited_by_count":15,"area":null},{"id":"2504.02107","title":"TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining","created":"2025-04-02","cited_by_count":15,"area":null},{"id":"2504.11373","title":"Cancer-Myth: Evaluating Large Language Models on Patient Questions with False Presuppositions","created":"2025-04-15","cited_by_count":15,"area":null},{"id":"2504.13128","title":"FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2505.20243","title":"It's High Time: A Survey of Temporal Question Answering","created":"2025-05-26","cited_by_count":14,"area":null},{"id":"2510.04226","title":"What and Whose Knowledge? Measuring Epistemic Diversity in Large Language Models","created":"2025-10-05","cited_by_count":14,"area":null},{"id":"2401.08664","title":"Adapting Large Language Models for Education: Foundational Capabilities, Potentials, and Challenges","created":"2023-12-27","cited_by_count":13,"area":null},{"id":"2405.05583","title":"OpenFactCheck: Building, Benchmarking Customized Fact-Checking Systems and Evaluating the Factuality of Claims and LLMs","created":"2024-05-09","cited_by_count":13,"area":null},{"id":"2410.14651","title":"Real-time Factuality Assessment from Adversarial Feedback","created":"2024-10-18","cited_by_count":12,"area":null},{"id":"2509.04656","title":"AraHalluEval: A Fine-grained Hallucination Evaluation Framework for Arabic LLMs","created":"2025-09-04","cited_by_count":12,"area":null},{"id":"2401.02575","title":"Large Language Models for Social Networks: Applications, Challenges, and Solutions","created":"2024-01-04","cited_by_count":11,"area":null},{"id":"2407.12982","title":"Retrieval-Enhanced Machine Learning: Synthesis and Opportunities","created":"2024-07-17","cited_by_count":11,"area":null},{"id":"2410.10083","title":"Beyond Graphs: Can Large Language Models Comprehend Hypergraphs?","created":"2024-10-14","cited_by_count":11,"area":null},{"id":"2502.11256","title":"Unveiling Environmental Impacts of Large Language Model Serving: A Functional Unit View","created":"2025-02-16","cited_by_count":11,"area":null},{"id":"2403.19113","title":"FACTOID: FACtual enTailment fOr hallucInation Detection","created":"2024-03-28","cited_by_count":10,"area":null},{"id":"2404.00942","title":"Evaluating the Factuality of Large Language Models using Large-Scale Knowledge Graphs","created":"2024-04-01","cited_by_count":10,"area":null},{"id":"2412.20251","title":"ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty","created":"2024-12-28","cited_by_count":10,"area":null},{"id":"2402.19103","title":"Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models","created":"2024-02-29","cited_by_count":9,"area":null},{"id":"2403.05266","title":"ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models","created":"2024-03-08","cited_by_count":9,"area":null},{"id":"2403.11169","title":"Customized large language models can outperform Community Notes in correcting misinformation","created":"2024-03-17","cited_by_count":9,"area":null},{"id":"2407.05868","title":"KG-FPQ: Evaluating Factuality Hallucination in LLMs with Knowledge Graph-based False Premise Questions","created":"2024-07-08","cited_by_count":9,"area":null},{"id":"2501.01059","title":"Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2403.13583","title":"CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing","created":"2024-03-20","cited_by_count":8,"area":null},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2410.07765","title":"GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2501.06699","title":"Large Language Models, Knowledge Graphs and Search Engines: A Crossroads for Answering Users' Questions","created":"2025-01-12","cited_by_count":8,"area":null},{"id":"2505.16973","title":"VeriFastScore: Speeding up long-form factuality evaluation","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2510.12839","title":"FaStfact: Faster, Stronger Long-Form Factuality Evaluations in LLMs","created":"2025-10-13","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":"2410.15116","title":"Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models","created":"2024-10-19","cited_by_count":7,"area":null},{"id":"2311.07424","title":"Hallucination Augmented Recitations for Language Models","created":"2023-11-13","cited_by_count":6,"area":null},{"id":"2311.08303","title":"Extrinsically-Focused Evaluation of Omissions in Medical Summarization","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2404.12045","title":"RAM: Towards an Ever-Improving Memory System by Learning from Communications","created":"2024-04-18","cited_by_count":6,"area":null},{"id":"2406.16294","title":"LangSuitE: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2503.08542","title":"CLEV: LLM-Based Evaluation Through Lightweight Efficient Voting for Free-Form Question-Answering","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2503.10690","title":"Battling Misinformation: An Empirical Study on Adversarial Factuality in Open-Source Large Language Models","created":"2025-03-12","cited_by_count":6,"area":null},{"id":"2504.13816","title":"Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations","created":"2025-04-18","cited_by_count":6,"area":null},{"id":"2507.05288","title":"A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models","created":"2025-07-05","cited_by_count":6,"area":null},{"id":"2508.00109","title":"FACTORY: A Challenging Human-Verified Prompt Set for Long-Form Factuality","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2510.07238","title":"When Benchmarks Age: Temporal Misalignment through Large Language Model Factuality Evaluation","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2512.16883","title":"AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning","created":"2025-12-18","cited_by_count":6,"area":null},{"id":"2403.12145","title":"Syn-QA2: Evaluating False Assumptions in Long-tail Questions with Synthetic QA Datasets","created":"2024-03-18","cited_by_count":5,"area":null},{"id":"2406.00975","title":"Luna: An Evaluation Foundation Model to Catch Language Model Hallucinations with High Accuracy and Low Cost","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2408.10490","title":"Analysis of Plan-based Retrieval for Grounded Text Generation","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2502.12769","title":"How Much Do LLMs Hallucinate across Languages? On Realistic Multilingual Estimation of LLM Hallucination","created":"2025-02-18","cited_by_count":5,"area":null},{"id":"2503.10673","title":"ZeroSumEval: An Extensible Framework For Scaling LLM Evaluation with Inter-Model Competition","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2504.12562","title":"ZeroSumEval: Scaling LLM Evaluation with Inter-Model Competition","created":"2025-04-17","cited_by_count":5,"area":null},{"id":"2505.21115","title":"Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2508.17771","title":"Speculating LLMs' Chinese Training Data Pollution from Their Tokens","created":"2025-08-25","cited_by_count":5,"area":null},{"id":"2511.11500","title":"Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation","created":"2025-11-14","cited_by_count":5,"area":null},{"id":"2601.07506","title":"Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluation","created":"2026-01-12","cited_by_count":5,"area":null}],"next_cursor":"100"}