{"total":221,"rows":[{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494,"area":null},{"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":"2405.01535","title":"Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models","created":"2024-05-02","cited_by_count":446,"area":null},{"id":"2404.18796","title":"Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models","created":"2024-04-29","cited_by_count":326,"area":null},{"id":"2410.12784","title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","created":"2024-10-16","cited_by_count":318,"area":null},{"id":"2406.07791","title":"Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge","created":"2024-06-12","cited_by_count":269,"area":null},{"id":"2406.12624","title":"Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges","created":"2024-06-18","cited_by_count":205,"area":null},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2402.14016","title":"Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment","created":"2024-02-21","cited_by_count":126,"area":null},{"id":"2407.18370","title":"Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement","created":"2024-07-25","cited_by_count":105,"area":null},{"id":"2403.02839","title":"An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4","created":"2024-03-05","cited_by_count":94,"area":null},{"id":"2403.18771","title":"CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklists","created":"2024-03-27","cited_by_count":94,"area":null},{"id":"2407.06551","title":"OffsetBias: Leveraging Debiased Data for Tuning Evaluators","created":"2024-07-09","cited_by_count":94,"area":null},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2503.02240","title":"OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale","created":"2025-03-04","cited_by_count":91,"area":null},{"id":"2501.10970","title":"The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs","created":"2025-01-19","cited_by_count":74,"area":null},{"id":"2402.01383","title":"LLM-based NLG Evaluation: Current Status and Challenges","created":"2024-02-02","cited_by_count":73,"area":null},{"id":"2407.01100","title":"Eliminating Position Bias of Language Models: A Mechanistic Approach","created":"2024-07-01","cited_by_count":65,"area":null},{"id":"2403.01131","title":"LLaMoCo: Instruction Tuning of Large Language Models for Optimization Code Generation","created":"2024-03-02","cited_by_count":45,"area":null},{"id":"2409.16191","title":"HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models","created":"2024-09-24","cited_by_count":44,"area":null},{"id":"2410.16256","title":"CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution","created":"2024-10-21","cited_by_count":42,"area":null},{"id":"2507.02856","title":"Answer Matching Outperforms Multiple Choice for Language Model Evaluation","created":"2025-07-03","cited_by_count":41,"area":null},{"id":"2503.05142","title":"RocketEval: Efficient Automated LLM Evaluation via Grading Checklist","created":"2025-03-07","cited_by_count":39,"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":"2508.06709","title":"Play Favorites: A Statistical Method to Measure Self-Bias in LLM-as-a-Judge","created":"2025-08-08","cited_by_count":36,"area":null},{"id":"2410.15393","title":"CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges","created":"2024-10-20","cited_by_count":34,"area":null},{"id":"2408.03907","title":"Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models","created":"2024-08-07","cited_by_count":33,"area":null},{"id":"2507.10535","title":"CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks","created":"2025-07-14","cited_by_count":33,"area":null},{"id":"2406.13439","title":"Finding Blind Spots in Evaluator LLMs with Interpretable Checklists","created":"2024-06-19","cited_by_count":32,"area":null},{"id":"2506.02592","title":"Beyond the Surface: Measuring Self-Preference in LLM Judgments","created":"2025-06-03","cited_by_count":31,"area":null},{"id":"2505.12201","title":"How Reliable is Multilingual LLM-as-a-Judge?","created":"2025-05-18","cited_by_count":30,"area":null},{"id":"2410.20774","title":"Are LLM-Judges Robust to Expressions of Uncertainty? Investigating the effect of Epistemic Markers on LLM-based Evaluation","created":"2024-10-28","cited_by_count":29,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2606.19544","title":"Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias","created":"2026-06-17","cited_by_count":28,"area":null},{"id":"2508.21184","title":"BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design","created":"2025-08-28","cited_by_count":24,"area":null},{"id":"2509.04013","title":"On Robustness and Reliability of Benchmark-Based Evaluation of LLMs","created":"2025-09-04","cited_by_count":23,"area":null},{"id":"2403.08010","title":"Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM","created":"2024-03-12","cited_by_count":21,"area":null},{"id":"2405.05253","title":"Open Source Language Models Can Provide Feedback: Evaluating LLMs' Ability to Help Students Using GPT-4-As-A-Judge","created":"2024-05-08","cited_by_count":20,"area":null},{"id":"2405.11724","title":"Token-wise Influential Training Data Retrieval for Large Language Models","created":"2024-05-20","cited_by_count":20,"area":null},{"id":"2410.05193","title":"RevisEval: Improving LLM-as-a-Judge via Response-Adapted References","created":"2024-10-07","cited_by_count":20,"area":null},{"id":"2501.07493","title":"Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards","created":"2025-01-13","cited_by_count":20,"area":null},{"id":"2405.11874","title":"xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation","created":"2024-05-20","cited_by_count":19,"area":null},{"id":"2410.02902","title":"Better Instruction-Following Through Minimum Bayes Risk","created":"2024-10-03","cited_by_count":19,"area":null},{"id":"2505.16222","title":"Don't Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation","created":"2025-05-22","cited_by_count":18,"area":null},{"id":"2508.06225","title":"Overconfidence in LLM-as-a-Judge: Diagnosis and Confidence-Driven Solution","created":"2025-08-08","cited_by_count":18,"area":null},{"id":"2408.14622","title":"What Makes a Good Story and How Can We Measure It? A Comprehensive Survey of Story Evaluation","created":"2024-08-26","cited_by_count":17,"area":null},{"id":"2409.16788","title":"Mitigating the Bias of Large Language Model Evaluation","created":"2024-09-25","cited_by_count":17,"area":null},{"id":"2505.17104","title":"P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark","created":"2025-05-21","cited_by_count":17,"area":null},{"id":"2404.08865","title":"LLM In-Context Recall is Prompt Dependent","created":"2024-04-13","cited_by_count":15,"area":null},{"id":"2406.11629","title":"Can Many-Shot In-Context Learning Help LLMs as Evaluators? A Preliminary Empirical Study","created":"2024-06-17","cited_by_count":15,"area":null},{"id":"2408.12942","title":"Causal-Guided Active Learning for Debiasing Large Language Models","created":"2024-08-23","cited_by_count":15,"area":null},{"id":"2402.13125","title":"TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning","created":"2024-02-20","cited_by_count":14,"area":null},{"id":"2412.14140","title":"GLIDER: Grading LLM Interactions and Decisions using Explainable Ranking","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2503.05977","title":"Is Your Video Language Model a Reliable Judge?","created":"2025-03-07","cited_by_count":14,"area":null},{"id":"2603.00039","title":"CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation","created":"2026-02-09","cited_by_count":13,"area":null},{"id":"2604.07666","title":"An Imperfect Verifier is Good Enough: Learning with Noisy Rewards","created":"2026-04-09","cited_by_count":13,"area":null},{"id":"2408.13704","title":"DHP Benchmark: Are LLMs Good NLG Evaluators?","created":"2024-08-25","cited_by_count":12,"area":null},{"id":"2507.09104","title":"CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards","created":"2025-07-12","cited_by_count":12,"area":null},{"id":"2409.19014","title":"FLEX: Expert-level False-Less EXecution Metric for Reliable Text-to-SQL Benchmark","created":"2024-09-24","cited_by_count":11,"area":null},{"id":"2501.17178","title":"Tuning LLM Judge Design Decisions for 1/1000 of the Cost","created":"2025-01-24","cited_by_count":11,"area":null},{"id":"2505.15433","title":"Set-LLM: A Permutation-Invariant LLM","created":"2025-05-21","cited_by_count":11,"area":null},{"id":"2403.06009","title":"Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations","created":"2024-03-09","cited_by_count":10,"area":null},{"id":"2402.12146","title":"Enabling Weak LLMs to Judge Response Reliability via Meta Ranking","created":"2024-02-19","cited_by_count":9,"area":null},{"id":"2504.04713","title":"Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts","created":"2025-04-07","cited_by_count":9,"area":null},{"id":"2506.00386","title":"Adaptive-VP: A Framework for LLM-Based Virtual Patients that Adapts to Trainees' Dialogue to Facilitate Nurse Communication Training","created":"2025-05-31","cited_by_count":9,"area":null},{"id":"2402.14860","title":"Ranking Large Language Models without Ground Truth","created":"2024-02-21","cited_by_count":8,"area":null},{"id":"2407.04873","title":"Evaluating Language Models for Generating and Judging Programming Feedback","created":"2024-07-05","cited_by_count":8,"area":null},{"id":"2503.04013","title":"Benchmarking Large Language Models on Multiple Tasks in Bioinformatics NLP with Prompting","created":"2025-03-06","cited_by_count":8,"area":null},{"id":"2505.03475","title":"am-ELO: A Stable Framework for Arena-based LLM Evaluation","created":"2025-05-06","cited_by_count":8,"area":null},{"id":"2505.11095","title":"Towards Better Evaluation for Generated Patent Claims","created":"2025-05-16","cited_by_count":8,"area":null},{"id":"2603.23522","title":"Qworld: Question-Specific Evaluation Criteria for LLMs","created":"2026-03-06","cited_by_count":8,"area":null},{"id":"2607.08535","title":"When the Judge Changes, So Does the Measurement: Auditing LLM-as-Judge Reliability","created":"2026-07-09","cited_by_count":8,"area":null},{"id":"2406.11102","title":"Grading Massive Open Online Courses Using Large Language Models","created":"2024-06-16","cited_by_count":7,"area":null},{"id":"2502.12477","title":"Savaal: Scalable Concept-Driven Question Generation to Enhance Human Learning","created":"2025-02-18","cited_by_count":7,"area":null},{"id":"2502.14445","title":"PredictaBoard: Benchmarking LLM Score Predictability","created":"2025-02-20","cited_by_count":7,"area":null},{"id":"2502.18018","title":"Verdict: A Library for Scaling Judge-Time Compute","created":"2025-02-25","cited_by_count":7,"area":null},{"id":"2510.19600","title":"Human-Agent Collaborative Paper-to-Page Crafting","created":"2025-10-22","cited_by_count":7,"area":null},{"id":"2601.08654","title":"From Rubrics to Reliable Scores: Evidence-Grounded Text Evaluation with LLM Judges","created":"2026-01-13","cited_by_count":7,"area":null},{"id":"2502.06633","title":"Combining Large Language Models with Static Analyzers for Code Review Generation","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2504.07421","title":"AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery","created":"2025-04-10","cited_by_count":6,"area":null},{"id":"2506.02945","title":"Quantitative LLM Judges","created":"2025-06-03","cited_by_count":6,"area":null},{"id":"2506.10403","title":"Time To Impeach LLM-as-a-Judge: Programs are the Future of Evaluation","created":"2025-06-12","cited_by_count":6,"area":null},{"id":"2508.08777","title":"Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge","created":"2025-08-12","cited_by_count":6,"area":null},{"id":"2510.12462","title":"Evaluating and Mitigating LLM-as-a-judge Bias in Communication Systems","created":"2025-10-14","cited_by_count":6,"area":null},{"id":"2606.06462","title":"Benchmark Everything Everywhere All at Once","created":"2026-06-04","cited_by_count":6,"area":null},{"id":"2403.04222","title":"Self-Evaluation of Large Language Model based on Glass-box Features","created":"2024-03-07","cited_by_count":5,"area":null},{"id":"2405.16552","title":"SED: Self-Evaluation Decoding Enhances Large Language Models for Better Generation","created":"2024-05-26","cited_by_count":5,"area":null},{"id":"2501.01743","title":"Automating Legal Interpretation with LLMs: Retrieval, Generation, and Evaluation","created":"2025-01-03","cited_by_count":5,"area":null},{"id":"2505.17691","title":"ELSPR: Evaluator LLM Training Data Self-Purification on Non-Transitive Preferences via Tournament Graph Reconstruction","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2508.12358","title":"Uncovering Systematic Failures of LLMs in Verifying Code Against Natural Language Specifications","created":"2025-08-17","cited_by_count":5,"area":null},{"id":"2510.00628","title":"Hearing the Order: Investigating Position Bias in Large Audio-Language Models","created":"2025-10-01","cited_by_count":5,"area":null},{"id":"2510.06538","title":"Auto-Prompt Ensemble for LLM Judge","created":"2025-10-08","cited_by_count":5,"area":null},{"id":"2601.07506","title":"Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluation","created":"2026-01-12","cited_by_count":5,"area":null},{"id":"2602.06625","title":"FairJudge: An Adaptive, Debiased, and Consistent LLM-as-a-Judge","created":"2026-02-06","cited_by_count":5,"area":null},{"id":"2405.00801","title":"\"Ask Me Anything\": How Comcast Uses LLMs to Assist Agents in Real Time","created":"2024-05-01","cited_by_count":4,"area":null},{"id":"2503.00847","title":"Argument Summarization and its Evaluation in the Era of Large Language Models","created":"2025-03-02","cited_by_count":4,"area":null},{"id":"2505.04209","title":"To Judge or not to Judge: Using LLM Judgements for Advertiser Keyphrase Relevance at eBay","created":"2025-05-07","cited_by_count":4,"area":null},{"id":"2505.12301","title":"Beyond Single-Point Judgment: Distribution Alignment for LLM-as-a-Judge","created":"2025-05-18","cited_by_count":4,"area":null},{"id":"2505.15240","title":"Generalised Probabilistic Modelling and Improved Uncertainty Estimation in Comparative LLM-as-a-judge","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2509.24678","title":"Reference-Free Rating of LLM Responses via Latent Information","created":"2025-09-29","cited_by_count":4,"area":null}],"next_cursor":"100"}