{"total":82,"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":"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":"2309.03883","title":"DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models","created":"2023-09-07","cited_by_count":376,"area":null},{"id":"2309.13788","title":"Can LLM-Generated Misinformation Be Detected?","created":"2023-09-25","cited_by_count":177,"area":null},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157,"area":null},{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127,"area":null},{"id":"2405.12819","title":"Large Language Models Meet NLP: A Survey","created":"2024-05-21","cited_by_count":103,"area":null},{"id":"2405.09589","title":"A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models","created":"2024-05-15","cited_by_count":100,"area":null},{"id":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97,"area":null},{"id":"2402.17811","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","created":"2024-02-27","cited_by_count":91,"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":"2402.02420","title":"Factuality of Large Language Models: A Survey","created":"2024-02-04","cited_by_count":66,"area":null},{"id":"2310.01382","title":"Compressing LLMs: The Truth is Rarely Pure and Never Simple","created":"2023-10-02","cited_by_count":62,"area":null},{"id":"2308.03656","title":"Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench","created":"2023-08-07","cited_by_count":54,"area":null},{"id":"2310.00935","title":"Resolving Knowledge Conflicts in Large Language Models","created":"2023-10-02","cited_by_count":50,"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":"2504.04635","title":"Steering off Course: Reliability Challenges in Steering Language Models","created":"2025-04-06","cited_by_count":34,"area":null},{"id":"2410.22685","title":"Improving Uncertainty Quantification in Large Language Models via Semantic Embeddings","created":"2024-10-30","cited_by_count":30,"area":null},{"id":"2310.12086","title":"FactCHD: Benchmarking Fact-Conflicting Hallucination Detection","created":"2023-10-18","cited_by_count":29,"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":"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":"2311.18580","title":"FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity","created":"2023-11-30","cited_by_count":25,"area":null},{"id":"2406.20015","title":"ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models","created":"2024-06-28","cited_by_count":25,"area":null},{"id":"2410.22257","title":"FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation","created":"2024-10-29","cited_by_count":25,"area":null},{"id":"2406.11267","title":"Mitigating Large Language Model Hallucination with Faithful Finetuning","created":"2024-06-17","cited_by_count":24,"area":null},{"id":"2311.15296","title":"UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation","created":"2023-11-26","cited_by_count":22,"area":null},{"id":"2309.02654","title":"Zero-Resource Hallucination Prevention for Large Language Models","created":"2023-09-06","cited_by_count":19,"area":null},{"id":"2404.05411","title":"Know When To Stop: A Study of Semantic Drift in Text Generation","created":"2024-04-08","cited_by_count":18,"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":"2311.16989","title":"ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?","created":"2023-11-28","cited_by_count":15,"area":null},{"id":"2401.05930","title":"SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully","created":"2024-01-11","cited_by_count":15,"area":null},{"id":"2403.00896","title":"DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Models","created":"2024-03-01","cited_by_count":15,"area":null},{"id":"2406.05494","title":"Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation","created":"2024-06-08","cited_by_count":15,"area":null},{"id":"2407.04693","title":"ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models","created":"2024-07-05","cited_by_count":14,"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":"2503.05757","title":"Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Models","created":"2025-02-22","cited_by_count":12,"area":null},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2406.07735","title":"REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy","created":"2024-06-11","cited_by_count":11,"area":null},{"id":"2410.03156","title":"MELODI: Exploring Memory Compression for Long Contexts","created":"2024-10-04","cited_by_count":11,"area":null},{"id":"2409.11798","title":"The Factuality of Large Language Models in the Legal Domain","created":"2024-09-18","cited_by_count":10,"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":"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":"2410.08970","title":"NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models","created":"2024-10-11","cited_by_count":9,"area":null},{"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":"2505.01731","title":"Efficient Shapley Value-based Non-Uniform Pruning of Large Language Models","created":"2025-05-03","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":"2405.20315","title":"ANAH: Analytical Annotation of Hallucinations in Large Language Models","created":"2024-05-30","cited_by_count":7,"area":null},{"id":"2502.03199","title":"Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models","created":"2025-02-05","cited_by_count":7,"area":null},{"id":"2503.12908","title":"HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models","created":"2025-03-17","cited_by_count":7,"area":null},{"id":"2406.09155","title":"DefAn: Definitive Answer Dataset for LLMs Hallucination Evaluation","created":"2024-06-13","cited_by_count":6,"area":null},{"id":"2410.13098","title":"A Little Human Data Goes A Long Way","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2412.11404","title":"Attention with Dependency Parsing Augmentation for Fine-Grained Attribution","created":"2024-12-16","cited_by_count":5,"area":null},{"id":"2407.11930","title":"Localizing and Mitigating Errors in Long-form Question Answering","created":"2024-07-16","cited_by_count":4,"area":null},{"id":"2608.01021","title":"Can Humans Dream of Electric Sheep? Human-Written Samples for Fine-Grained Vision-and-Language Hallucination Benchmarking","created":"2026-08-02","cited_by_count":4,"area":null},{"id":"2409.11233","title":"Evaluating the Impact of Compression Techniques on Task-Specific Performance of Large Language Models","created":"2024-09-17","cited_by_count":3,"area":null},{"id":"2410.12278","title":"Controlled Automatic Task-Specific Synthetic Data Generation for Hallucination Detection","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2503.22989","title":"FindTheFlaws: Annotated Errors for Detecting Flawed Reasoning and Scalable Oversight Research","created":"2025-03-29","cited_by_count":3,"area":null},{"id":"2507.04404","title":"LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers","created":"2025-07-06","cited_by_count":3,"area":null},{"id":"2507.19586","title":"Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning","created":"2025-07-25","cited_by_count":3,"area":null},{"id":"2604.10733","title":"Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2407.13297","title":"SpeciaLex: A Benchmark for In-Context Specialized Lexicon Learning","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2504.06219","title":"Can Performant LLMs Be Ethical? Quantifying the Impact of Web Crawling Opt-Outs","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2505.17793","title":"Compression Hacking: A Supplementary Perspective on Informatics Properties of Language Models from Geometric Distortion","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2503.21813","title":"OAEI-LLM-T: A TBox Benchmark Dataset for Understanding Large Language Model Hallucinations in Ontology Matching","created":"2025-03-25","cited_by_count":1,"area":null},{"id":"2504.10167","title":"C-FAITH: A Chinese Fine-Grained Benchmark for Automated Hallucination Evaluation","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2601.15714","title":"Even GPT-5.2 Can't Count to Five: The Case for Zero-Error Horizons in Trustworthy LLMs","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2601.18901","title":"Self-Aware Knowledge Probing: Evaluating Language Models' Relational Knowledge through Confidence Calibration","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2608.23705","title":"The Limits of Automatic Evaluation of Creativity in Large Language Models","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2609.04539","title":"A Calibrated Reflection Approach for Enhancing Confidence Estimation in LLMs","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2609.05505","title":"SciLitBench: Benchmark and Design Principles for LLM-Powered Systematic Literature Reviews","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2407.12812","title":"Building Understandable Messaging for Policy and Evidence Review (BUMPER) with AI","created":"2024-06-27","cited_by_count":0,"area":null},{"id":"2408.08769","title":"Lower Layers Matter: Alleviating Hallucination via Multi-Layer Fusion Contrastive Decoding with Truthfulness Refocused","created":"2024-08-16","cited_by_count":0,"area":null},{"id":"2410.11366","title":"LargePiG: Your Large Language Model is Secretly a Pointer Generator","created":"2024-10-15","cited_by_count":0,"area":null},{"id":"2410.20340","title":"Maintaining Informative Coherence: Migrating Hallucinations in Large Language Models via Absorbing Markov Chains","created":"2024-10-27","cited_by_count":0,"area":null},{"id":"2501.12975","title":"OnionEval: An Unified Evaluation of Fact-conflicting Hallucination for Small-Large Language Models","created":"2025-01-22","cited_by_count":0,"area":null},{"id":"2506.04907","title":"Context Is Not Comprehension","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2509.23417","title":"Retrieval-Constrained Decoding Reveals Underestimated Parametric Knowledge in Language Models","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2601.06196","title":"Geometry-Aware Hallucination Detection in Large Language Models","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2606.00819","title":"Mitigating Hallucinations in Large Language Models Via Decoder Layer Skipping","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.26437","title":"ConflictScore: Identifying and Measuring How Language Models Handle Conflicting Evidence","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.23067","title":"Attention-Guided Layer Selection for Contrastive Decoding in Large Language Models","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2610.19344","title":"Target-Token Asymmetry Can Masquerade As Depth Specialization","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}