{"total":18,"rows":[{"id":"2309.17012","title":"Benchmarking Cognitive Biases in Large Language Models as Evaluators","created":"2023-09-29","cited_by_count":150,"area":null},{"id":"2305.14938","title":"Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark","created":"2023-05-24","cited_by_count":63,"area":null},{"id":"2304.13861","title":"The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks","created":"2023-04-26","cited_by_count":35,"area":null},{"id":"2311.09799","title":"How Far Can We Extract Diverse Perspectives from Large Language Models?","created":"2023-11-16","cited_by_count":22,"area":null},{"id":"2205.11097","title":"A Fine-grained Interpretability Evaluation Benchmark for Neural NLP","created":"2022-05-23","cited_by_count":15,"area":null},{"id":"2308.07902","title":"Through the Lens of Core Competency: Survey on Evaluation of Large Language Models","created":"2023-08-15","cited_by_count":12,"area":null},{"id":"2406.11622","title":"Building Knowledge-Guided Lexica to Model Cultural Variation","created":"2024-06-17","cited_by_count":11,"area":null},{"id":"2407.03545","title":"On Evaluating Explanation Utility for Human-AI Decision Making in NLP","created":"2024-07-03","cited_by_count":9,"area":null},{"id":"2402.01980","title":"SOCIALITE-LLAMA: An Instruction-Tuned Model for Social Scientific Tasks","created":"2024-02-03","cited_by_count":7,"area":null},{"id":"2209.10876","title":"An Attention Matrix for Every Decision: Faithfulness-based Arbitration Among Multiple Attention-Based Interpretations of Transformers in Text Classification","created":"2022-09-22","cited_by_count":6,"area":null},{"id":"2210.07469","title":"StyLEx: Explaining Style Using Human Lexical Annotations","created":"2022-10-14","cited_by_count":3,"area":null},{"id":"2402.13006","title":"Investigating the Impact of Model Instability on Explanations and Uncertainty","created":"2024-02-20","cited_by_count":3,"area":null},{"id":"2212.09873","title":"A Comparative Study on Textual Saliency of Styles from Eye Tracking, Annotations, and Language Models","created":"2022-12-19","cited_by_count":2,"area":null},{"id":"2310.07135","title":"Comparing Styles across Languages: A Cross-Cultural Exploration of Politeness","created":"2023-10-11","cited_by_count":2,"area":null},{"id":"2502.01270","title":"Main Predicate and Their Arguments as Explanation Signals For Intent Classification","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2502.13326","title":"Capturing Human Cognitive Styles with Language: Towards an Experimental Evaluation Paradigm","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2210.14406","title":"RedPen: Region- and Reason-Annotated Dataset of Unnatural Speech","created":"2022-10-26","cited_by_count":0,"area":null},{"id":"2504.04640","title":"Splits! Flexible Sociocultural Linguistic Investigation at Scale","created":"2025-04-06","cited_by_count":0,"area":null}],"next_cursor":null}