{"total":34,"rows":[{"id":"2310.07641","title":"Evaluating Large Language Models at Evaluating Instruction Following","created":"2023-10-11","cited_by_count":302,"area":null},{"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":"2211.00295","title":"CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation","created":"2022-11-01","cited_by_count":39,"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":"2305.09022","title":"It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance","created":"2023-05-15","cited_by_count":26,"area":null},{"id":"2210.03256","title":"Not another Negation Benchmark: The NaN-NLI Test Suite for Sub-clausal Negation","created":"2022-10-06","cited_by_count":25,"area":null},{"id":"2204.12708","title":"On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations","created":"2022-04-27","cited_by_count":19,"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":"2406.05494","title":"Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation","created":"2024-06-08","cited_by_count":15,"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":"2306.16638","title":"A negation detection assessment of GPTs: analysis with the xNot360 dataset","created":"2023-06-29","cited_by_count":10,"area":null},{"id":"2406.07492","title":"Paraphrasing in Affirmative Terms Improves Negation Understanding","created":"2024-06-11","cited_by_count":8,"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":"2305.14785","title":"Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2305.19500","title":"Exploring Lottery Prompts for Pre-trained Language Models","created":"2023-05-31","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":"2301.03238","title":"MAQA: A Multimodal QA Benchmark for Negation","created":"2023-01-09","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":"2502.07717","title":"Making Language Models Robust Against Negation","created":"2025-02-11","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":"2408.05793","title":"SAGA: A Participant-specific Examination of Story Alternatives and Goal Applicability for a Deeper Understanding of Complex Events","created":"2024-08-11","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":"2305.17401","title":"A Framework For Refining Text Classification and Object Recognition from Academic Articles","created":"2023-05-27","cited_by_count":1,"area":null},{"id":"2306.10241","title":"Snowman: A Million-scale Chinese Commonsense Knowledge Graph Distilled from Foundation Model","created":"2023-06-17","cited_by_count":1,"area":null},{"id":"2311.03021","title":"Detecting agreement in multi-party dialogue: evaluating speaker diarisation versus a procedural baseline to enhance user engagement","created":"2023-11-06","cited_by_count":1,"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":"2504.00584","title":"Semantic Adapter for Universal Text Embeddings: Diagnosing and Mitigating Negation Blindness to Enhance Universality","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2609.16396","title":"Negation Beyond the Verbal Channel: Temporal Multimodal Correlates in Dialogue","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2307.05034","title":"Synthetic Dataset for Evaluating Complex Compositional Knowledge for Natural Language Inference","created":"2023-07-11","cited_by_count":0,"area":null},{"id":"2411.00056","title":"Generating Diverse Negations from Affirmative Sentences","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2510.20375","title":"The Impact of Negated Text on Hallucination with Large Language Models","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2603.12423","title":"Interpreting Negation in GPT-2: Layer- and Head-Level Causal Analysis","created":"2026-03-12","cited_by_count":0,"area":null}],"next_cursor":null}