{"total":30,"rows":[{"id":"2410.02185","title":"POSIX: A Prompt Sensitivity Index For Large Language Models","created":"2024-10-03","cited_by_count":59,"area":null},{"id":"2410.14516","title":"Do LLMs \"know\" internally when they follow instructions?","created":"2024-10-18","cited_by_count":26,"area":null},{"id":"2404.05729","title":"Finding Visual Task Vectors","created":"2024-04-08","cited_by_count":24,"area":null},{"id":"2406.10099","title":"Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuning","created":"2024-06-14","cited_by_count":16,"area":null},{"id":"2406.19898","title":"Paraphrase Types Elicit Prompt Engineering Capabilities","created":"2024-06-28","cited_by_count":15,"area":null},{"id":"2504.12408","title":"A Human-AI Comparative Analysis of Prompt Sensitivity in LLM-Based Relevance Judgment","created":"2025-04-16","cited_by_count":15,"area":null},{"id":"2412.06484","title":"Small Languages, Big Models: A Study of Continual Training on Languages of Norway","created":"2024-12-09","cited_by_count":12,"area":null},{"id":"2506.06950","title":"What Makes a Good Natural Language Prompt?","created":"2025-06-07","cited_by_count":7,"area":null},{"id":"2409.03735","title":"Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2411.02398","title":"Prompting with Phonemes: Enhancing LLMs' Multilinguality for Non-Latin Script Languages","created":"2024-11-04","cited_by_count":6,"area":null},{"id":"2503.10542","title":"Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2504.16188","title":"FinNLI: Novel Dataset for Multi-Genre Financial Natural Language Inference Benchmarking","created":"2025-04-22","cited_by_count":3,"area":null},{"id":"2406.10950","title":"E-Bench: Towards Evaluating the Ease-of-Use of Large Language Models","created":"2024-06-16","cited_by_count":2,"area":null},{"id":"2501.07718","title":"Benchmarking Abstractive Summarisation: A Dataset of Human-authored Summaries of Norwegian News Articles","created":"2025-01-13","cited_by_count":2,"area":null},{"id":"2408.09365","title":"Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting","created":"2024-08-18","cited_by_count":1,"area":null},{"id":"2510.26193","title":"RCScore: Quantifying Response Consistency in Large Language Models","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2603.21373","title":"PLR: Plackett-Luce for Reordering In-Context Learning Examples","created":"2026-03-22","cited_by_count":1,"area":null},{"id":"2411.10813","title":"Information Anxiety in Large Language Models","created":"2024-11-16","cited_by_count":0,"area":null},{"id":"2502.07101","title":"SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2505.08389","title":"Towards Contamination Resistant Benchmarks","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2508.07975","title":"Improving Document Retrieval Coherence for Semantically Equivalent Queries","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2603.09994","title":"Evaluating Adjective-Noun Compositionality in LLMs: Functional vs Representational Perspectives","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2604.15385","title":"Prompt-Driven Code Summarization: A Systematic Literature Review","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.21786","title":"From Codebooks to VLMs: Evaluating Automated Visual Discourse Analysis for Climate Change on Social Media","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.29678","title":"Spurious Prompts: Can Irrelevant Prompts Steer Large Language Models?","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.29816","title":"Harnessing non-adversarial robustness in large language models","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.12117","title":"Soft-Prompt Tuning for Fair and Efficient LLM Benchmark Evaluation","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2608.18539","title":"Evaluating and Explaining Prompt Sensitivity of LLMs Using Interactions","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.20349","title":"Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2610.19872","title":"RCCM: Diagnosing Gains and Harms in Reasoning-Prompt Transfer","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}