{"total":26,"rows":[{"id":"2307.08153","title":"Analyzing Dataset Annotation Quality Management in the Wild","created":"2023-07-16","cited_by_count":41,"area":null},{"id":"2211.16285","title":"Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches","created":"2022-11-29","cited_by_count":39,"area":null},{"id":"2403.02270","title":"FENICE: Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction","created":"2024-03-04","cited_by_count":28,"area":null},{"id":"2210.12814","title":"RuCoLA: Russian Corpus of Linguistic Acceptability","created":"2022-10-23","cited_by_count":26,"area":null},{"id":"2110.08514","title":"Analyzing Dynamic Adversarial Training Data in the Limit","created":"2021-10-16","cited_by_count":24,"area":null},{"id":"2312.17543","title":"Building Efficient Universal Classifiers with Natural Language Inference","created":"2023-12-29","cited_by_count":22,"area":null},{"id":"2411.05375","title":"Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking","created":"2024-11-08","cited_by_count":18,"area":null},{"id":"2410.07473","title":"Localizing Factual Inconsistencies in Attributable Text Generation","created":"2024-10-09","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":"2502.08080","title":"NLI under the Microscope: What Atomic Hypothesis Decomposition Reveals","created":"2025-02-12","cited_by_count":11,"area":null},{"id":"2204.10615","title":"Generalized Quantifiers as a Source of Error in Multilingual NLU Benchmarks","created":"2022-04-22","cited_by_count":8,"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":"2212.10057","title":"WeCheck: Strong Factual Consistency Checker via Weakly Supervised Learning","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2503.19260","title":"Linguistic Blind Spots of Large Language Models","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2305.18917","title":"Fighting Bias with Bias: Promoting Model Robustness by Amplifying Dataset Biases","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2307.02269","title":"SpaceNLI: Evaluating the Consistency of Predicting Inferences in Space","created":"2023-07-05","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":"2503.07282","title":"A Graph-based Verification Framework for Fact-Checking","created":"2025-03-10","cited_by_count":4,"area":null},{"id":"2511.07659","title":"Revisiting NLI: Towards Cost-Effective and Human-Aligned Metrics for Evaluating LLMs in Question Answering","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2210.03068","title":"InferES : A Natural Language Inference Corpus for Spanish Featuring Negation-Based Contrastive and Adversarial Examples","created":"2022-10-06","cited_by_count":3,"area":null},{"id":"2510.05046","title":"COLE: a Comprehensive Benchmark for French Language Understanding Evaluation","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2305.15130","title":"On Degrees of Freedom in Defining and Testing Natural Language Understanding","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2603.11991","title":"BTZSC: A Benchmark for Zero-Shot Text Classification Across Cross-Encoders, Embedding Models, Rerankers and LLMs","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2408.04114","title":"Zero-shot Factual Consistency Evaluation Across Domains","created":"2024-08-07","cited_by_count":0,"area":null},{"id":"2410.07094","title":"An Approach for Auto Generation of Labeling Functions for Software Engineering Chatbots","created":"2024-10-09","cited_by_count":0,"area":null},{"id":"2603.26449","title":"ClimateCheck 2026: Scientific Fact-Checking and Disinformation Narrative Classification of Climate-related Claims","created":"2026-03-27","cited_by_count":0,"area":null}],"next_cursor":null}