{"total":31,"rows":[{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"area":null},{"id":"2504.05228","title":"NoveltyBench: Evaluating Language Models for Humanlike Diversity","created":"2025-04-07","cited_by_count":66,"area":null},{"id":"2410.02683","title":"DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life","created":"2024-10-03","cited_by_count":59,"area":null},{"id":"2503.05061","title":"No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding","created":"2025-03-07","cited_by_count":54,"area":null},{"id":"2503.03064","title":"Improving LLM-as-a-Judge Inference with the Judgment Distribution","created":"2025-03-04","cited_by_count":37,"area":null},{"id":"2412.03205","title":"U-MATH: A University-Level Benchmark for Evaluating Mathematical Skills in LLMs","created":"2024-12-04","cited_by_count":24,"area":null},{"id":"2411.19146","title":"Puzzle: Distillation-Based NAS for Inference-Optimized LLMs","created":"2024-11-28","cited_by_count":17,"area":null},{"id":"2505.13772","title":"Krikri: Advancing Open Large Language Models for Greek","created":"2025-05-19","cited_by_count":14,"area":null},{"id":"2512.20578","title":"Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits","created":"2025-12-23","cited_by_count":14,"area":null},{"id":"2507.10540","title":"FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data","created":"2025-07-14","cited_by_count":10,"area":null},{"id":"2506.10060","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","created":"2025-06-11","cited_by_count":8,"area":null},{"id":"2502.06329","title":"Expect the Unexpected: FailSafe Long Context QA for Finance","created":"2025-02-10","cited_by_count":7,"area":null},{"id":"2506.02945","title":"Quantitative LLM Judges","created":"2025-06-03","cited_by_count":6,"area":null},{"id":"2507.19219","title":"How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation under the One-Time-Pad-Based Framework","created":"2025-07-25","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2503.11858","title":"OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2412.15256","title":"Structured Extraction of Real World Medical Knowledge using LLMs for Summarization and Search","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2501.14499","title":"Automated Assignment Grading with Large Language Models: Insights From a Bioinformatics Course","created":"2025-01-24","cited_by_count":3,"area":null},{"id":"2505.24768","title":"From Macro to Micro: Probing Dataset Diversity in Language Model Fine-Tuning","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2509.18901","title":"Extractive Fact Decomposition for Interpretable Natural Language Inference in one Forward Pass","created":"2025-09-23","cited_by_count":3,"area":null},{"id":"2504.19594","title":"Mapping the Italian Telegram Ecosystem: Communities, Toxicity, and Hate Speech","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2606.11762","title":"Automated Creativity Evaluation of Language Models Across Open-Ended Tasks","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2607.20216","title":"Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2501.00562","title":"An Overview and Discussion on Using Large Language Models for Implementation Generation of Solutions to Open-Ended Problems","created":"2024-12-31","cited_by_count":0,"area":null},{"id":"2503.02948","title":"ExpertGenQA: Open-ended QA generation in Specialized Domains","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2508.06060","title":"LLMs for Resource Allocation: A Participatory Budgeting Approach to Inferring Preferences","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2509.15027","title":"CLEAR: A Comprehensive Linguistic Evaluation of Argument Rewriting by Large Language Models","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2512.14500","title":"C-ing Clearly: Enhanced Binary Code Explanations using C code","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2605.07925","title":"How Value Induction Reshapes LLM Behaviour","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.00846","title":"CUPID in the Model Zoo: Online Matchmaking for Selecting Your Dream LLM","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2610.10092","title":"I would rather quit NLP than read another paper like this: The rise of antithesis in NLP papers","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}