{"total":19,"rows":[{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2306.08189","title":"Language models are not naysayers: An analysis of language models on negation benchmarks","created":"2023-06-14","cited_by_count":74,"area":null},{"id":"2310.15941","title":"This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models","created":"2023-10-24","cited_by_count":18,"area":null},{"id":"2307.13989","title":"This is not correct! Negation-aware Evaluation of Language Generation Systems","created":"2023-07-26","cited_by_count":17,"area":null},{"id":"2210.14486","title":"Leveraging Affirmative Interpretations from Negation Improves Natural Language Understanding","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2506.14397","title":"Thunder-NUBench: A Benchmark for LLMs' Sentence-Level Negation Understanding","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2311.03663","title":"Principles from Clinical Research for NLP Model Generalization","created":"2023-11-07","cited_by_count":4,"area":null},{"id":"2504.17311","title":"FLUKE: A Linguistically-Driven and Task-Agnostic Framework for Robustness Evaluation","created":"2025-04-24","cited_by_count":3,"area":null},{"id":"2311.07556","title":"Using Natural Language Explanations to Improve Robustness of In-context Learning","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2404.02421","title":"Revisiting subword tokenization: A case study on affixal negation in large language models","created":"2024-04-03","cited_by_count":2,"area":null},{"id":"2506.02378","title":"Exploring Explanations Improves the Robustness of In-Context Learning","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2407.02432","title":"Evaluating the Robustness of Adverse Drug Event Classification Models Using Templates","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2507.20419","title":"Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2411.00056","title":"Generating Diverse Negations from Affirmative Sentences","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2501.17569","title":"A linguistically-motivated evaluation methodology for unraveling model's abilities in reading comprehension tasks","created":"2025-01-29","cited_by_count":0,"area":null},{"id":"2601.04693","title":"Thunder-KoNUBench: A Corpus-Aligned Benchmark for Korean Negation Understanding","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2609.13685","title":"Not all Negation Cues are Equal: Affixal Negations Yield Better Negation Understanding","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.33530","title":"E-CONAN (Entailment, CONtradition And Neutral) Diagnostics Dataset Investigating Linguistic Phenomena in Arabic Natural Language Understanding","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.05278","title":"When Verifiable Counts Depend on Wording: Auditing Wording Robustness in Instruction Following","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}