{"total":16,"rows":[{"id":"2104.06598","title":"AR-LSAT: Investigating Analytical Reasoning of Text","created":"2021-04-14","cited_by_count":51,"area":null},{"id":"2105.03659","title":"Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text","created":"2021-05-08","cited_by_count":46,"area":null},{"id":"2402.01742","title":"Towards Optimizing the Costs of LLM Usage","created":"2024-01-29","cited_by_count":33,"area":null},{"id":"2104.08825","title":"Flexible Generation of Natural Language Deductions","created":"2021-04-18","cited_by_count":28,"area":null},{"id":"2402.11100","title":"When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models","created":"2024-02-16","cited_by_count":22,"area":null},{"id":"2404.04963","title":"SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials","created":"2024-04-07","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":"2206.11147","title":"reStructured Pre-training","created":"2022-06-22","cited_by_count":8,"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":"2401.08089","title":"A Study on Training and Developing Large Language Models for Behavior Tree Generation","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2112.02333","title":"LoNLI: An Extensible Framework for Testing Diverse Logical Reasoning Capabilities for NLI","created":"2021-12-04","cited_by_count":3,"area":null},{"id":"2204.06283","title":"Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding","created":"2022-04-13","cited_by_count":3,"area":null},{"id":"2509.18901","title":"Extractive Fact Decomposition for Interpretable Natural Language Inference in one Forward Pass","created":"2025-09-23","cited_by_count":3,"area":null},{"id":"2203.00162","title":"Do Transformers know symbolic rules, and would we know if they did?","created":"2022-02-19","cited_by_count":1,"area":null},{"id":"2505.02235","title":"SEval-Ex: A Statement-Level Framework for Explainable Summarization Evaluation","created":"2025-05-04","cited_by_count":1,"area":null},{"id":"2609.33699","title":"SpecRead: A Benchmark for Measuring Whether Language Models Understand Hardware Specifications","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}