{"total":37,"rows":[{"id":"2405.14782","title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","created":"2024-05-23","cited_by_count":179,"area":null},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157,"area":null},{"id":"2501.00274","title":"LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts","created":"2024-12-31","cited_by_count":87,"area":null},{"id":"2406.20052","title":"Understanding and Mitigating Language Confusion in LLMs","created":"2024-06-28","cited_by_count":75,"area":null},{"id":"2410.03608","title":"TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation","created":"2024-10-04","cited_by_count":68,"area":null},{"id":"2405.14394","title":"Instruction Tuning With Loss Over Instructions","created":"2024-05-23","cited_by_count":40,"area":null},{"id":"2406.15053","title":"PARIKSHA: A Large-Scale Investigation of Human-LLM Evaluator Agreement on Multilingual and Multi-Cultural Data","created":"2024-06-21","cited_by_count":37,"area":null},{"id":"2412.13091","title":"LMUnit: Fine-grained Evaluation with Natural Language Unit Tests","created":"2024-12-17","cited_by_count":33,"area":null},{"id":"2404.07900","title":"High-Dimension Human Value Representation in Large Language Models","created":"2024-04-11","cited_by_count":20,"area":null},{"id":"2402.13887","title":"Beyond Probabilities: Unveiling the Misalignment in Evaluating Large Language Models","created":"2024-02-21","cited_by_count":19,"area":null},{"id":"2409.10566","title":"Eureka: Evaluating and Understanding Large Foundation Models","created":"2024-09-13","cited_by_count":18,"area":null},{"id":"2311.13133","title":"LIMIT: Less Is More for Instruction Tuning Across Evaluation Paradigms","created":"2023-11-22","cited_by_count":14,"area":null},{"id":"2404.11288","title":"A Preference-driven Paradigm for Enhanced Translation with Large Language Models","created":"2024-04-17","cited_by_count":9,"area":null},{"id":"2507.17015","title":"Can External Validation Tools Improve Annotation Quality for LLM-as-a-Judge?","created":"2025-07-22","cited_by_count":9,"area":null},{"id":"2508.15218","title":"Are Checklists Really Useful for Automatic Evaluation of Generative Tasks?","created":"2025-08-21","cited_by_count":9,"area":null},{"id":"2509.03116","title":"Measuring Scalar Constructs in Social Science with LLMs","created":"2025-09-03","cited_by_count":9,"area":null},{"id":"2409.13641","title":"Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning","created":"2024-09-20","cited_by_count":5,"area":null},{"id":"2603.29791","title":"Reasoning-Driven Synthetic Data Generation and Evaluation","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2507.13138","title":"Assessing the Reliability of LLMs Annotations in the Context of Demographic Bias and Model Explanation","created":"2025-07-17","cited_by_count":4,"area":null},{"id":"2409.00696","title":"Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation","created":"2024-09-01","cited_by_count":3,"area":null},{"id":"2503.13102","title":"REPA: Russian Error Types Annotation for Evaluating Text Generation and Judgment Capabilities","created":"2025-03-17","cited_by_count":3,"area":null},{"id":"2603.04409","title":"Unpacking Human Preference for LLMs: Demographically Aware Evaluation with the HUMAINE Framework","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2605.30504","title":"Auditing LLM Benchmarks with Item Response Theory","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2602.17185","title":"The Bots of Persuasion: Examining How Conversational Agents' Linguistic Expressions of Personality Affect User Perceptions and Decisions","created":"2026-02-19","cited_by_count":2,"area":null},{"id":"2603.00883","title":"Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2603.16120","title":"Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Users","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2604.25224","title":"ValueBlindBench: Agreement-Gated Stress Testing of LLM-Judged Investment Rationales Before Returns Are Observable","created":"2026-04-28","cited_by_count":2,"area":null},{"id":"2504.01248","title":"Automated Factual Benchmarking for In-Car Conversational Systems using Large Language Models","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2509.15336","title":"Knowledge-Driven Hallucination in Large Language Models: An Empirical Study on Process Modeling","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2510.07892","title":"Metric Calculating Benchmark: Code-Verifiable Complicate Instruction Following Benchmark for Large Language Models","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2605.13307","title":"PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2506.23979","title":"TaP: A Taxonomy-Guided Framework for Automated and Scalable Preference Data Generation","created":"2025-06-30","cited_by_count":0,"area":null},{"id":"2508.09544","title":"SYNAPSE-G: Bridging Large Language Models and Graph Learning for Rare Event Classification","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2601.07229","title":"DiSCo: Making Absence Visible in Intelligent Summarization Interfaces","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2607.05123","title":"ASSEMCAD: Production-Ready CAD Assembly Generation from Natural Language","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.02617","title":"Preferred, Not Safer: Pairwise Preference Is a Poor Proxy for Clinical Safety","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2608.23783","title":"Inter-dimension Dependence for Multi-Dimensional Evaluation of Open-Ended Text","created":"2026-08-24","cited_by_count":0,"area":null}],"next_cursor":null}