{"total":77,"rows":[{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075,"area":null},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525,"area":null},{"id":"2305.11747","title":"HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","created":"2023-05-19","cited_by_count":341,"area":null},{"id":"2305.16739","title":"AlignScore: Evaluating Factual Consistency with a Unified Alignment Function","created":"2023-05-26","cited_by_count":288,"area":null},{"id":"2401.00396","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","created":"2023-12-31","cited_by_count":283,"area":"rag"},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256,"area":null},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2305.13281","title":"LM vs LM: Detecting Factual Errors via Cross Examination","created":"2023-05-22","cited_by_count":156,"area":null},{"id":"2307.16877","title":"Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering","created":"2023-07-31","cited_by_count":151,"area":null},{"id":"2401.06855","title":"Fine-grained Hallucination Detection and Editing for Language Models","created":"2024-01-12","cited_by_count":149,"area":null},{"id":"2303.01432","title":"WiCE: Real-World Entailment for Claims in Wikipedia","created":"2023-03-02","cited_by_count":120,"area":null},{"id":"2204.10757","title":"FaithDial: A Faithful Benchmark for Information-Seeking Dialogue","created":"2022-04-22","cited_by_count":109,"area":null},{"id":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97,"area":null},{"id":"2309.06794","title":"Cognitive Mirage: A Review of Hallucinations in Large Language Models","created":"2023-09-13","cited_by_count":84,"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":"2308.06374","title":"Large Language Models and Knowledge Graphs: Opportunities and Challenges","created":"2023-08-11","cited_by_count":71,"area":null},{"id":"2305.14292","title":"WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia","created":"2023-05-23","cited_by_count":67,"area":null},{"id":"2310.00741","title":"FELM: Benchmarking Factuality Evaluation of Large Language Models","created":"2023-10-01","cited_by_count":66,"area":null},{"id":"2110.08222","title":"DialFact: A Benchmark for Fact-Checking in Dialogue","created":"2021-10-15","cited_by_count":62,"area":null},{"id":"2305.13194","title":"SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation","created":"2023-05-22","cited_by_count":42,"area":null},{"id":"2310.06498","title":"A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection","created":"2023-10-10","cited_by_count":42,"area":null},{"id":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2401.14367","title":"Genie: Achieving Human Parity in Content-Grounded Datasets Generation","created":"2024-01-25","cited_by_count":31,"area":null},{"id":"2303.17574","title":"Elastic Weight Removal for Faithful and Abstractive Dialogue Generation","created":"2023-03-30","cited_by_count":29,"area":null},{"id":"2203.05227","title":"Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2402.15089","title":"AttributionBench: How Hard is Automatic Attribution Evaluation?","created":"2024-02-23","cited_by_count":26,"area":null},{"id":"2412.06676","title":"I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token","created":"2024-12-09","cited_by_count":26,"area":null},{"id":"2405.17980","title":"Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering","created":"2024-05-28","cited_by_count":25,"area":null},{"id":"2403.07726","title":"SemEval-2024 Shared Task 6: SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes","created":"2024-03-12","cited_by_count":24,"area":null},{"id":"2310.02932","title":"Assessing Large Language Models on Climate Information","created":"2023-10-04","cited_by_count":23,"area":null},{"id":"2310.13189","title":"Fast and Accurate Factual Inconsistency Detection Over Long Documents","created":"2023-10-19","cited_by_count":23,"area":null},{"id":"2402.17630","title":"Fine-Grained Natural Language Inference Based Faithfulness Evaluation for Diverse Summarisation Tasks","created":"2024-02-27","cited_by_count":23,"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":"2310.08372","title":"Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment","created":"2023-10-12","cited_by_count":19,"area":null},{"id":"2408.15533","title":"LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagation","created":"2024-08-28","cited_by_count":17,"area":"rag"},{"id":"2406.00252","title":"Towards Rationality in Language and Multimodal Agents: A Survey","created":"2024-06-01","cited_by_count":16,"area":"agents"},{"id":"2402.12368","title":"A synthetic data approach for domain generalization of NLI models","created":"2024-02-19","cited_by_count":15,"area":"synth"},{"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":"2410.18359","title":"Improving Model Factuality with Fine-grained Critique-based Evaluator","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2309.06490","title":"Leveraging Large Language Models for Automated Dialogue Analysis","created":"2023-09-12","cited_by_count":14,"area":null},{"id":"2305.16819","title":"With a Little Push, NLI Models can Robustly and Efficiently Predict Faithfulness","created":"2023-05-26","cited_by_count":13,"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":"2409.17073","title":"Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition","created":"2024-09-25","cited_by_count":12,"area":null},{"id":"2305.12191","title":"Pointwise Mutual Information Based Metric and Decoding Strategy for Faithful Generation in Document Grounded Dialogs","created":"2023-05-20","cited_by_count":11,"area":null},{"id":"2305.07355","title":"ZARA: Improving Few-Shot Self-Rationalization for Small Language Models","created":"2023-05-12","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":"2508.15396","title":"Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Models","created":"2025-08-21","cited_by_count":7,"area":null},{"id":"2311.08117","title":"Insights into Classifying and Mitigating LLMs' Hallucinations","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2410.09949","title":"MisinfoEval: Generative AI in the Era of \"Alternative Facts\"","created":"2024-10-13","cited_by_count":6,"area":null},{"id":"2504.18114","title":"Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection","created":"2025-04-25","cited_by_count":6,"area":null},{"id":"2310.18794","title":"Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generation","created":"2023-10-28","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":"2407.05474","title":"Enhancing Hallucination Detection through Perturbation-Based Synthetic Data Generation in System Responses","created":"2024-07-07","cited_by_count":5,"area":"synth"},{"id":"2403.14578","title":"RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain","created":"2024-03-21","cited_by_count":4,"area":null},{"id":"2404.03344","title":"Schroedinger's Threshold: When the AUC doesn't predict Accuracy","created":"2024-04-04","cited_by_count":4,"area":null},{"id":"2210.17418","title":"Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model","created":"2022-10-31","cited_by_count":3,"area":null},{"id":"2502.08109","title":"HuDEx: Integrating Hallucination Detection and Explainability for Enhancing the Reliability of LLM responses","created":"2025-02-12","cited_by_count":3,"area":null},{"id":"2305.14658","title":"Evaluate What You Can't Evaluate: Unassessable Quality for Generated Response","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2310.18364","title":"From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning","created":"2023-10-24","cited_by_count":2,"area":"lr"},{"id":"2309.10413","title":"PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems","created":"2023-09-19","cited_by_count":1,"area":null},{"id":"2404.07836","title":"Question Generation in Knowledge-Driven Dialog: Explainability and Evaluation","created":"2024-04-11","cited_by_count":1,"area":null},{"id":"2405.13984","title":"Less for More: Enhanced Feedback-aligned Mixed LLMs for Molecule Caption Generation and Fine-Grained NLI Evaluation","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2409.16658","title":"Pre-trained Language Models Return Distinguishable Probability Distributions to Unfaithfully Hallucinated Texts","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2411.00878","title":"Exploring the Knowledge Mismatch Hypothesis: Hallucination Propensity in Small Models Fine-tuned on Data from Larger Models","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2411.03300","title":"VERITAS: A Unified Approach to Reliability Evaluation","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2510.21118","title":"The Gray Zone of Faithfulness: Taming Ambiguity in Unfaithfulness Detection","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2510.27052","title":"VISTA: Verification In Sequential Turn-based Assessment","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2311.00953","title":"Blending Reward Functions via Few Expert Demonstrations for Faithful and Accurate Knowledge-Grounded Dialogue Generation","created":"2023-11-02","cited_by_count":0,"area":"alignment"},{"id":"2405.15110","title":"CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2408.00675","title":"Leveraging Entailment Judgements in Cross-Lingual Summarisation","created":"2024-08-01","cited_by_count":0,"area":null},{"id":"2509.21104","title":"PerHalluEval: Persian Hallucination Evaluation Benchmark for Large Language Models","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2606.23915","title":"Do LLM Attribution Metrics Transfer? Auditing Retrieval-Augmented Generation Evaluation Across Datasets and Constructs","created":"2026-06-22","cited_by_count":0,"area":"rag"},{"id":"2609.01810","title":"TalkFa: A Unified Benchmark for Farsi Dialogue Generation and Understanding","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.04806","title":"When Financial Fine-tuning Fails: A Three-Level Detectability Analysis of Numerical Hallucination in Domain-Adapted Language Models","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.07152","title":"An Auditable Symbolic-RAG-Generative AI Architecture for Goal-Oriented Conversation Orchestration","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.35804","title":"Evaluating the Effects of Prompt Perturbation on Bias and Hallucination in Large Language Models","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2610.12989","title":"Language Models Have Interpretable Narrative Mechanisms","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}