{"total":62,"rows":[{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075,"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":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256,"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":"2307.06908","title":"Generating Benchmarks for Factuality Evaluation of Language Models","created":"2023-07-13","cited_by_count":105,"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":"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":"2503.22458","title":"Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey","created":"2025-03-28","cited_by_count":57,"area":"agents"},{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2210.13865","title":"Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation","created":"2022-10-25","cited_by_count":45,"area":null},{"id":"2204.07447","title":"Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusters","created":"2022-04-15","cited_by_count":44,"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":"2205.12673","title":"InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning","created":"2022-05-25","cited_by_count":39,"area":null},{"id":"2301.04449","title":"Diving Deep into Modes of Fact Hallucinations in Dialogue Systems","created":"2023-01-11","cited_by_count":32,"area":null},{"id":"2310.12086","title":"FactCHD: Benchmarking Fact-Conflicting Hallucination Detection","created":"2023-10-18","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":"2310.13189","title":"Fast and Accurate Factual Inconsistency Detection Over Long Documents","created":"2023-10-19","cited_by_count":23,"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":"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":"2309.06490","title":"Leveraging Large Language Models for Automated Dialogue Analysis","created":"2023-09-12","cited_by_count":14,"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":"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":"2308.04813","title":"CLEVA: Chinese Language Models EVAluation Platform","created":"2023-08-09","cited_by_count":13,"area":null},{"id":"2210.08511","title":"CDConv: A Benchmark for Contradiction Detection in Chinese Conversations","created":"2022-10-16","cited_by_count":10,"area":null},{"id":"2211.01587","title":"Eliciting Knowledge from Large Pre-Trained Models for Unsupervised Knowledge-Grounded Conversation","created":"2022-11-03","cited_by_count":10,"area":null},{"id":"2212.09180","title":"Don't Forget Your ABC's: Evaluating the State-of-the-Art in Chat-Oriented Dialogue Systems","created":"2022-12-18","cited_by_count":9,"area":null},{"id":"2204.04991","title":"TRUE: Re-evaluating Factual Consistency Evaluation","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2205.09314","title":"Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation","created":"2022-05-19","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":"2212.10057","title":"WeCheck: Strong Factual Consistency Checker via Weakly Supervised Learning","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2304.14318","title":"q2d: Turning Questions into Dialogs to Teach Models How to Search","created":"2023-04-27","cited_by_count":5,"area":null},{"id":"2311.08195","title":"Automated Fact-Checking in Dialogue: Are Specialized Models Needed?","created":"2023-11-14","cited_by_count":5,"area":null},{"id":"2405.18344","title":"The Battle of LLMs: A Comparative Study in Conversational QA Tasks","created":"2024-05-28","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":"2502.16766","title":"ATEB: Evaluating and Improving Advanced NLP Tasks for Text Embedding Models","created":"2025-02-24","cited_by_count":5,"area":null},{"id":"2212.10557","title":"DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines","created":"2022-12-20","cited_by_count":4,"area":null},{"id":"2305.15026","title":"Transferring Visual Attributes from Natural Language to Verified Image Generation","created":"2023-05-24","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":"2304.03325","title":"ChatGPT-Crawler: Find out if ChatGPT really knows what it's talking about","created":"2023-04-06","cited_by_count":3,"area":null},{"id":"2309.14966","title":"Interactively Learning Social Media Representations Improves News Source Factuality Detection","created":"2023-09-26","cited_by_count":3,"area":null},{"id":"2311.17376","title":"CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogs","created":"2023-11-29","cited_by_count":3,"area":null},{"id":"2603.19281","title":"URAG: A Benchmark for Uncertainty Quantification in Retrieval-Augmented Large Language Models","created":"2026-03-02","cited_by_count":3,"area":"rag"},{"id":"2311.06121","title":"Multilingual and Multi-topical Benchmark of Fine-tuned Language models and Large Language Models for Check-Worthy Claim Detection","created":"2023-11-10","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":"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":"2508.01862","title":"Counterfactual Probing for Hallucination Detection and Mitigation in Large Language Models","created":"2025-08-03","cited_by_count":1,"area":null},{"id":"2508.05782","title":"FineDialFact: A benchmark for Fine-grained Dialogue Fact Verification","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2509.15896","title":"The Psychology of Falsehood: A Human-Centric Survey of Misinformation Detection","created":"2025-09-19","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":"2601.03051","title":"Temporal Graph Network: Hallucination Detection in Multi-Turn Conversation","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2602.18448","title":"INSURE-Dial: A Phase-Aware Conversational Dataset & Benchmark for Compliance Verification and Phase Detection","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2604.16767","title":"When Misinformation Speaks and Converses: Rethinking Fact-Checking in Audio Platforms","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2606.11420","title":"Context-Aware Multimodal Claim Verification in Spoken Dialogues","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2408.16264","title":"LoraMap: Harnessing the Power of LoRA Connections","created":"2024-08-29","cited_by_count":0,"area":null},{"id":"2602.16298","title":"MultiCW: A Large-Scale Balanced Benchmark Dataset for Training Robust Check-Worthiness Detection Models","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2604.14389","title":"BiCon-Gate: Consistency-Gated De-colloquialisation for Dialogue Fact-Checking","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2609.04452","title":"TRILOGUE: A Trilingual Spoken Dialogue Fact-Checking Benchmark with Evidence and Paired Audio","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}