{"total":38,"rows":[{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222,"area":null},{"id":"2205.12411","title":"Linear Connectivity Reveals Generalization Strategies","created":"2022-05-24","cited_by_count":56,"area":null},{"id":"2212.10003","title":"(QA)$^2$: Question Answering with Questionable Assumptions","created":"2022-12-20","cited_by_count":51,"area":null},{"id":"2106.14282","title":"A Closer Look at How Fine-tuning Changes BERT","created":"2021-06-27","cited_by_count":42,"area":null},{"id":"2211.00295","title":"CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation","created":"2022-11-01","cited_by_count":39,"area":null},{"id":"2307.10234","title":"SentimentGPT: Exploiting GPT for Advanced Sentiment Analysis and its Departure from Current Machine Learning","created":"2023-07-16","cited_by_count":38,"area":null},{"id":"2104.05824","title":"Evaluating Saliency Methods for Neural Language Models","created":"2021-04-12","cited_by_count":37,"area":null},{"id":"2104.06511","title":"\"I'm Not Mad\": Commonsense Implications of Negation and Contradiction","created":"2021-04-13","cited_by_count":26,"area":null},{"id":"2106.01195","title":"Figurative Language in Recognizing Textual Entailment","created":"2021-06-02","cited_by_count":26,"area":null},{"id":"2104.05904","title":"DirectProbe: Studying Representations without Classifiers","created":"2021-04-13","cited_by_count":25,"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":"2205.03472","title":"When a sentence does not introduce a discourse entity, Transformer-based models still sometimes refer to it","created":"2022-05-06","cited_by_count":23,"area":null},{"id":"2103.03872","title":"Rissanen Data Analysis: Examining Dataset Characteristics via Description Length","created":"2021-03-05","cited_by_count":22,"area":null},{"id":"2111.08546","title":"Interpreting Language Models Through Knowledge Graph Extraction","created":"2021-11-16","cited_by_count":14,"area":null},{"id":"2305.17311","title":"Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models","created":"2023-05-27","cited_by_count":12,"area":null},{"id":"2404.04332","title":"Scope Ambiguities in Large Language Models","created":"2024-04-05","cited_by_count":11,"area":null},{"id":"2112.07874","title":"Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling","created":"2021-12-15","cited_by_count":10,"area":null},{"id":"2402.17467","title":"Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2109.11491","title":"Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords","created":"2021-09-23","cited_by_count":9,"area":null},{"id":"2107.07229","title":"Trusting RoBERTa over BERT: Insights from CheckListing the Natural Language Inference Task","created":"2021-07-15","cited_by_count":8,"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":"2106.01077","title":"SyGNS: A Systematic Generalization Testbed Based on Natural Language Semantics","created":"2021-06-02","cited_by_count":7,"area":null},{"id":"2105.14668","title":"On the Interplay Between Fine-tuning and Composition in Transformers","created":"2021-05-31","cited_by_count":6,"area":null},{"id":"2403.03028","title":"Word Importance Explains How Prompts Affect Language Model Outputs","created":"2024-03-05","cited_by_count":6,"area":null},{"id":"2503.13390","title":"Aligned Probing: Relating Toxic Behavior and Model Internals","created":"2025-03-17","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":"2506.04534","title":"Is It JUST Semantics? A Case Study of Discourse Particle Understanding in LLMs","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2104.07623","title":"Sometimes We Want Translationese","created":"2021-04-15","cited_by_count":3,"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":"2106.11054","title":"Visual Probing: Cognitive Framework for Explaining Self-Supervised Image Representations","created":"2021-06-21","cited_by_count":2,"area":null},{"id":"2210.02526","title":"\"No, they did not\": Dialogue response dynamics in pre-trained language models","created":"2022-10-05","cited_by_count":1,"area":null},{"id":"2302.08150","title":"Reanalyzing L2 Preposition Learning with Bayesian Mixed Effects and a Pretrained Language Model","created":"2023-02-16","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},{"id":"2503.06137","title":"Evaluating Discourse Cohesion in Pre-trained Language Models","created":"2025-03-08","cited_by_count":1,"area":null},{"id":"2512.13374","title":"Behavior and Representation in Open-Weight Large Language Models for Combinatorial Optimization: From Feature Extraction to Algorithm Selection","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2601.21191","title":"Function Words as Statistical Cues for Language Learning","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2106.02363","title":"Learning Slice-Aware Representations with Mixture of Attentions","created":"2021-06-04","cited_by_count":0,"area":null},{"id":"2403.06301","title":"LIEDER: Linguistically-Informed Evaluation for Discourse Entity Recognition","created":"2024-03-10","cited_by_count":0,"area":null}],"next_cursor":null}