{"total":41,"rows":[{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202,"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":"2202.07654","title":"Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation","created":"2022-02-15","cited_by_count":67,"area":null},{"id":"2205.06938","title":"Generating Literal and Implied Subquestions to Fact-check Complex Claims","created":"2022-05-14","cited_by_count":66,"area":null},{"id":"2212.10003","title":"(QA)$^2$: Question Answering with Questionable Assumptions","created":"2022-12-20","cited_by_count":51,"area":null},{"id":"2108.06130","title":"Semantic Answer Similarity for Evaluating Question Answering Models","created":"2021-08-13","cited_by_count":47,"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":"2305.03695","title":"Vera: A General-Purpose Plausibility Estimation Model for Commonsense Statements","created":"2023-05-05","cited_by_count":44,"area":null},{"id":"2211.11875","title":"Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference","created":"2022-11-21","cited_by_count":40,"area":null},{"id":"2107.02153","title":"FaVIQ: FAct Verification from Information-seeking Questions","created":"2021-07-05","cited_by_count":36,"area":null},{"id":"2305.16635","title":"Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing","created":"2023-05-26","cited_by_count":31,"area":null},{"id":"2210.04982","title":"REV: Information-Theoretic Evaluation of Free-Text Rationales","created":"2022-10-10","cited_by_count":22,"area":null},{"id":"2305.14824","title":"Mitigating Temporal Misalignment by Discarding Outdated Facts","created":"2023-05-24","cited_by_count":21,"area":null},{"id":"2404.12447","title":"AmbigDocs: Reasoning across Documents on Different Entities under the Same Name","created":"2024-04-18","cited_by_count":21,"area":null},{"id":"2502.19110","title":"Conformal Linguistic Calibration: Trading-off between Factuality and Specificity","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2202.06167","title":"Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference","created":"2022-02-12","cited_by_count":17,"area":null},{"id":"2307.09254","title":"Selective Generation for Controllable Language Models","created":"2023-07-18","cited_by_count":15,"area":null},{"id":"2405.06524","title":"Prompting Large Language Models with Knowledge Graphs for Question Answering Involving Long-tail Facts","created":"2024-05-10","cited_by_count":14,"area":null},{"id":"2405.16702","title":"Accurate and Nuanced Open-QA Evaluation Through Textual Entailment","created":"2024-05-26","cited_by_count":13,"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":"2305.19271","title":"Concise Answers to Complex Questions: Summarization of Long-form Answers","created":"2023-05-30","cited_by_count":7,"area":null},{"id":"2404.12145","title":"From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2212.01476","title":"NarraSum: A Large-Scale Dataset for Abstractive Narrative Summarization","created":"2022-12-02","cited_by_count":5,"area":null},{"id":"2311.07099","title":"Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning","created":"2023-11-13","cited_by_count":4,"area":null},{"id":"2402.18678","title":"RORA: Robust Free-Text Rationale Evaluation","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2403.04400","title":"Exploring Continual Learning of Compositional Generalization in NLI","created":"2024-03-07","cited_by_count":4,"area":null},{"id":"2203.10249","title":"Learning-by-Narrating: Narrative Pre-Training for Zero-Shot Dialogue Comprehension","created":"2022-03-19","cited_by_count":3,"area":null},{"id":"2211.12641","title":"Leveraging Data Recasting to Enhance Tabular Reasoning","created":"2022-11-23","cited_by_count":3,"area":null},{"id":"2312.04032","title":"RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2504.16188","title":"FinNLI: Novel Dataset for Multi-Genre Financial Natural Language Inference Benchmarking","created":"2025-04-22","cited_by_count":3,"area":null},{"id":"2111.07119","title":"Extracting and filtering paraphrases by bridging natural language inference and paraphrasing","created":"2021-11-13","cited_by_count":2,"area":null},{"id":"2403.17431","title":"Robust and Scalable Model Editing for Large Language Models","created":"2024-03-26","cited_by_count":2,"area":null},{"id":"2504.01450","title":"CASCADE Your Datasets for Cross-Mode Knowledge Retrieval of Language Models","created":"2025-04-02","cited_by_count":2,"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":"2603.19264","title":"Generative Active Testing: Efficient LLM Evaluation via Proxy Task Adaptation","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2207.00187","title":"An Understanding-Oriented Robust Machine Reading Comprehension Model","created":"2022-07-01","cited_by_count":0,"area":null},{"id":"2211.05598","title":"Using contradictions improves question answering systems","created":"2022-09-28","cited_by_count":0,"area":null},{"id":"2403.18803","title":"Projective Methods for Mitigating Gender Bias in Pre-trained Language Models","created":"2024-03-27","cited_by_count":0,"area":null},{"id":"2602.04982","title":"BioACE: An Automated Framework for Biomedical Answer and Citation Evaluations","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2609.00492","title":"The Privacy-Hallucination Tradeoff in Differentially Private Language Models","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.01369","title":"How Correct Is Your Answer? A Semantic Correctness Framework for Open QA Evaluation","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}