{"total":17,"rows":[{"id":"2212.09689","title":"Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor","created":"2022-12-19","cited_by_count":397,"area":null},{"id":"2401.00595","title":"State of What Art? A Call for Multi-Prompt LLM Evaluation","created":"2023-12-31","cited_by_count":310,"area":null},{"id":"2307.09009","title":"How is ChatGPT's behavior changing over time?","created":"2023-07-18","cited_by_count":270,"area":null},{"id":"2405.17202","title":"Efficient multi-prompt evaluation of LLMs","created":"2024-05-27","cited_by_count":73,"area":null},{"id":"2306.14924","title":"LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Coding","created":"2023-06-23","cited_by_count":64,"area":null},{"id":"2405.11357","title":"Large Language Models Lack Understanding of Character Composition of Words","created":"2024-05-18","cited_by_count":22,"area":null},{"id":"2312.01082","title":"A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness","created":"2023-12-02","cited_by_count":14,"area":null},{"id":"2305.07378","title":"Surfacing Biases in Large Language Models using Contrastive Input Decoding","created":"2023-05-12","cited_by_count":11,"area":null},{"id":"2307.05454","title":"Empowering Cross-lingual Behavioral Testing of NLP Models with Typological Features","created":"2023-07-11","cited_by_count":6,"area":null},{"id":"2406.10366","title":"Improving the Validity and Practical Usefulness of AI/ML Evaluations Using an Estimands Framework","created":"2024-06-14","cited_by_count":6,"area":null},{"id":"2506.23929","title":"IMPACT: Inflectional Morphology Probes Across Complex Typologies","created":"2025-06-30","cited_by_count":4,"area":null},{"id":"2508.02591","title":"CharBench: Evaluating the Role of Tokenization in Character-Level Tasks","created":"2025-08-04","cited_by_count":3,"area":null},{"id":"2509.19590","title":"Position: AI Evaluations Should be Grounded on a Theory of Capability","created":"2025-09-23","cited_by_count":2,"area":null},{"id":"2506.17369","title":"Re-Evaluating Code LLM Benchmarks Under Semantic Mutation","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2310.05378","title":"Transcending the Attention Paradigm: Representation Learning from Geospatial Social Media Data","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2508.05468","title":"TASE: Token Awareness and Structured Evaluation for Multilingual Language Models","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2604.19189","title":"Headlines You Won't Forget: Can Pronoun Insertion Increase Memorability?","created":"2026-04-21","cited_by_count":0,"area":null}],"next_cursor":null}