{"total":41,"rows":[{"id":"2306.10193","title":"Conformal Language Modeling","created":"2023-06-16","cited_by_count":170,"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":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97,"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":"2305.11171","title":"TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models","created":"2023-05-18","cited_by_count":83,"area":null},{"id":"2310.12150","title":"Understanding Retrieval Augmentation for Long-Form Question Answering","created":"2023-10-18","cited_by_count":45,"area":null},{"id":"2212.10622","title":"mFACE: Multilingual Summarization with Factual Consistency Evaluation","created":"2022-12-20","cited_by_count":42,"area":null},{"id":"2212.10750","title":"PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition","created":"2022-12-21","cited_by_count":29,"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":"2311.04335","title":"Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations","created":"2023-11-07","cited_by_count":20,"area":null},{"id":"2305.13214","title":"Atomic Inference for NLI with Generated Facts as Atoms","created":"2023-05-22","cited_by_count":18,"area":null},{"id":"2404.05904","title":"The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models","created":"2024-04-08","cited_by_count":17,"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":"2211.16853","title":"Revisiting text decomposition methods for NLI-based factuality scoring of summaries","created":"2022-11-30","cited_by_count":14,"area":null},{"id":"2401.16475","title":"InfoLossQA: Characterizing and Recovering Information Loss in Text Simplification","created":"2024-01-29","cited_by_count":14,"area":null},{"id":"2209.03755","title":"Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems","created":"2022-09-07","cited_by_count":12,"area":null},{"id":"2305.12641","title":"A Comprehensive Survey of Sentence Representations: From the BERT Epoch to the ChatGPT Era and Beyond","created":"2023-05-22","cited_by_count":12,"area":null},{"id":"2311.09182","title":"ContraDoc: Understanding Self-Contradictions in Documents with Large Language Models","created":"2023-11-15","cited_by_count":12,"area":null},{"id":"2304.13180","title":"Sebis at SemEval-2023 Task 7: A Joint System for Natural Language Inference and Evidence Retrieval from Clinical Trial Reports","created":"2023-04-25","cited_by_count":9,"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":"2305.14205","title":"$\\mu$PLAN: Summarizing using a Content Plan as Cross-Lingual Bridge","created":"2023-05-23","cited_by_count":7,"area":null},{"id":"2305.19585","title":"LAIT: Efficient Multi-Segment Encoding in Transformers with Layer-Adjustable Interaction","created":"2023-05-31","cited_by_count":7,"area":null},{"id":"2212.03222","title":"LawngNLI: A Long-Premise Benchmark for In-Domain Generalization from Short to Long Contexts and for Implication-Based Retrieval","created":"2022-12-06","cited_by_count":6,"area":null},{"id":"2305.14847","title":"Drafting Event Schemas using Language Models","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2404.15588","title":"Minimal Evidence Group Identification for Claim Verification","created":"2024-04-24","cited_by_count":5,"area":null},{"id":"2310.18431","title":"SDOH-NLI: a Dataset for Inferring Social Determinants of Health from Clinical Notes","created":"2023-10-27","cited_by_count":4,"area":null},{"id":"2408.04246","title":"Explicating the Implicit: Argument Detection Beyond Sentence Boundaries","created":"2024-08-08","cited_by_count":4,"area":null},{"id":"2212.10791","title":"OpineSum: Entailment-based self-training for abstractive opinion summarization","created":"2022-12-21","cited_by_count":3,"area":null},{"id":"2510.11928","title":"Discrepancy Detection at the Data Level: Toward Consistent Multilingual Question Answering","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2310.04592","title":"From Nuisance to News Sense: Augmenting the News with Cross-Document Evidence and Context","created":"2023-10-06","cited_by_count":1,"area":null},{"id":"2403.15351","title":"Multi-Review Fusion-in-Context","created":"2024-03-22","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":"2502.05793","title":"On Reference (In-)Determinacy in Natural Language Inference","created":"2025-02-09","cited_by_count":1,"area":null},{"id":"2601.21387","title":"User-Centric Evidence Ranking for Attribution and Fact Verification","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2211.05598","title":"Using contradictions improves question answering systems","created":"2022-09-28","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":"2502.05650","title":"Incongruence Identification in Eyewitness Testimony","created":"2025-02-08","cited_by_count":0,"area":null},{"id":"2601.02627","title":"Improved Evidence Extraction and Metrics for Document Inconsistency Detection with LLMs","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2609.03580","title":"HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.30571","title":"HARDEN: Constrained Evolutionary Search for Harder, Answer-Preserving Evaluation Cases","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}