{"total":35,"rows":[{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841,"area":null},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739,"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":"2305.05976","title":"Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge","created":"2023-05-10","cited_by_count":32,"area":null},{"id":"2305.07614","title":"NevIR: Negation in Neural Information Retrieval","created":"2023-05-12","cited_by_count":29,"area":null},{"id":"2404.12452","title":"Characterizing LLM Abstention Behavior in Science QA with Context Perturbations","created":"2024-04-18","cited_by_count":26,"area":null},{"id":"2504.01282","title":"Prompt-Reverse Inconsistency: LLM Self-Inconsistency Beyond Generative Randomness and Prompt Paraphrasing","created":"2025-04-02","cited_by_count":14,"area":null},{"id":"2410.15512","title":"Reverse Question Answering: Can an LLM Write a Question so Hard (or Bad) that it Can't Answer?","created":"2024-10-20","cited_by_count":13,"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":"2402.11409","title":"Multi-dimensional Evaluation of Empathetic Dialog Responses","created":"2024-02-18","cited_by_count":10,"area":null},{"id":"2405.05966","title":"Natural Language Processing RELIES on Linguistics","created":"2024-05-09","cited_by_count":9,"area":null},{"id":"2409.05653","title":"WinoPron: Revisiting English Winogender Schemas for Consistency, Coverage, and Grammatical Case","created":"2024-09-09","cited_by_count":9,"area":null},{"id":"2505.22830","title":"What Has Been Lost with Synthetic Evaluation?","created":"2025-05-28","cited_by_count":9,"area":null},{"id":"2406.07492","title":"Paraphrasing in Affirmative Terms Improves Negation Understanding","created":"2024-06-11","cited_by_count":8,"area":null},{"id":"2306.16722","title":"Evaluating Paraphrastic Robustness in Textual Entailment Models","created":"2023-06-29","cited_by_count":7,"area":null},{"id":"2311.09694","title":"Whispers of Doubt Amidst Echoes of Triumph in NLP Robustness","created":"2023-11-16","cited_by_count":5,"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":"2310.16135","title":"Can You Follow Me? Testing Situational Understanding in ChatGPT","created":"2023-10-24","cited_by_count":4,"area":null},{"id":"2507.22337","title":"A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers","created":"2025-07-30","cited_by_count":4,"area":null},{"id":"2403.01185","title":"Balancing Exploration and Exploitation in LLM using Soft RLLF for Enhanced Negation Understanding","created":"2024-03-02","cited_by_count":3,"area":null},{"id":"2409.06481","title":"NeIn: Telling What You Don't Want","created":"2024-09-09","cited_by_count":3,"area":null},{"id":"2502.07717","title":"Making Language Models Robust Against Negation","created":"2025-02-11","cited_by_count":3,"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":"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":"2505.12592","title":"PromptPrism: A Linguistically-Inspired Taxonomy for Prompts","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2510.08224","title":"Investigating Counterclaims in Causality Extraction from Text","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2310.13781","title":"How Much Consistency Is Your Accuracy Worth?","created":"2023-10-20","cited_by_count":1,"area":null},{"id":"2404.16262","title":"Interpreting Answers to Yes-No Questions in Dialogues from Multiple Domains","created":"2024-04-25","cited_by_count":1,"area":null},{"id":"2404.08666","title":"Revealing Trends in Datasets from the 2022 ACL and EMNLP Conferences","created":"2024-03-31","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":"2604.19921","title":"Commonsense Knowledge with Negation: A Resource to Enhance Negation Understanding","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2606.16867","title":"Revisiting the Systematicity in Negation in the Era of In-Context Learning","created":"2026-06-15","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":"2610.18579","title":"Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}