{"total":22,"rows":[{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2101.04840","title":"Robustness Gym: Unifying the NLP Evaluation Landscape","created":"2021-01-13","cited_by_count":108,"area":null},{"id":"2110.14566","title":"IndoNLI: A Natural Language Inference Dataset for Indonesian","created":"2021-10-27","cited_by_count":24,"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":"2404.02403","title":"Benchmarking Large Language Models for Persian: A Preliminary Study Focusing on ChatGPT","created":"2024-04-03","cited_by_count":11,"area":null},{"id":"2206.14729","title":"longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks","created":"2022-06-29","cited_by_count":8,"area":null},{"id":"2106.01077","title":"SyGNS: A Systematic Generalization Testbed Based on Natural Language Semantics","created":"2021-06-02","cited_by_count":7,"area":null},{"id":"2311.04449","title":"Recursion in Recursion: Two-Level Nested Recursion for Length Generalization with Scalability","created":"2023-11-08","cited_by_count":5,"area":null},{"id":"2103.08955","title":"Coordinate Constructions in English Enhanced Universal Dependencies: Analysis and Computational Modeling","created":"2021-03-16","cited_by_count":4,"area":null},{"id":"2106.03983","title":"Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference","created":"2021-06-07","cited_by_count":4,"area":null},{"id":"2307.10779","title":"Efficient Beam Tree Recursion","created":"2023-07-20","cited_by_count":4,"area":null},{"id":"2404.00748","title":"Benchmark Transparency: Measuring the Impact of Data on Evaluation","created":"2024-03-31","cited_by_count":4,"area":null},{"id":"2410.03429","title":"How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamics","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2209.04761","title":"Testing Pre-trained Language Models' Understanding of Distributivity via Causal Mediation Analysis","created":"2022-09-11","cited_by_count":3,"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":"2401.10353","title":"Inconsistent dialogue responses and how to recover from them","created":"2024-01-18","cited_by_count":3,"area":null},{"id":"2505.23191","title":"ExpeTrans: LLMs Are Experiential Transfer Learners","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2107.03884","title":"CANDLE: Decomposing Conditional and Conjunctive Queries for Task-Oriented Dialogue Systems","created":"2021-07-08","cited_by_count":1,"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":"2311.18712","title":"CoRec: An Easy Approach for Coordination Recognition","created":"2023-11-30","cited_by_count":1,"area":null},{"id":"2502.04797","title":"Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks","created":"2025-02-07","cited_by_count":1,"area":null}],"next_cursor":null}