{"total":663,"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":"2503.02240","title":"OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale","created":"2025-03-04","cited_by_count":91,"area":null},{"id":"2502.11221","title":"PlanGenLLMs: A Modern Survey of LLM Planning Capabilities","created":"2025-02-16","cited_by_count":83,"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":"2502.11528","title":"A Survey of Personalized Large Language Models: Progress and Future Directions","created":"2025-02-17","cited_by_count":71,"area":null},{"id":"2505.16707","title":"KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models","created":"2025-05-22","cited_by_count":71,"area":null},{"id":"2505.23802","title":"MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks","created":"2025-05-26","cited_by_count":64,"area":null},{"id":"2502.14127","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","created":"2025-02-19","cited_by_count":52,"area":null},{"id":"2510.07284","title":"Online Rubrics Elicitation from Pairwise Comparisons","created":"2025-10-08","cited_by_count":46,"area":null},{"id":"2506.07962","title":"Correlated Errors in Large Language Models","created":"2025-06-09","cited_by_count":45,"area":null},{"id":"2506.22316","title":"Evaluating Scoring Bias in LLM-as-a-Judge","created":"2025-06-27","cited_by_count":43,"area":null},{"id":"2503.01013","title":"TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop","created":"2025-03-02","cited_by_count":39,"area":null},{"id":"2505.15957","title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","created":"2025-05-21","cited_by_count":39,"area":null},{"id":"2510.27106","title":"Rating Roulette: Self-Inconsistency in LLM-As-A-Judge Frameworks","created":"2025-10-31","cited_by_count":38,"area":null},{"id":"2502.14815","title":"Optimizing Model Selection for Compound AI Systems","created":"2025-02-20","cited_by_count":36,"area":null},{"id":"2503.17489","title":"Judge Anything: MLLM as a Judge Across Any Modality","created":"2025-03-21","cited_by_count":34,"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":"2502.12904","title":"Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements","created":"2025-02-18","cited_by_count":32,"area":null},{"id":"2507.16280","title":"ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquiry","created":"2025-07-22","cited_by_count":32,"area":null},{"id":"2501.08579","title":"LLM-based Human Simulations Have Not Yet Been Reliable","created":"2025-01-15","cited_by_count":30,"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":"2506.21621","title":"The Open Proof Corpus: A Large-Scale Study of LLM-Generated Mathematical Proofs","created":"2025-06-23","cited_by_count":30,"area":null},{"id":"2511.21140","title":"How to Correctly Report LLM-as-a-Judge Evaluations","created":"2025-11-26","cited_by_count":30,"area":null},{"id":"2506.07673","title":"How Benchmark Prediction from Fewer Data Misses the Mark","created":"2025-06-09","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":"2509.18658","title":"Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction","created":"2025-09-23","cited_by_count":27,"area":null},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2501.12862","title":"Mutation-Guided LLM-based Test Generation at Meta","created":"2025-01-22","cited_by_count":25,"area":null},{"id":"2502.11736","title":"ReviewEval: An Evaluation Framework for AI-Generated Reviews","created":"2025-02-17","cited_by_count":25,"area":null},{"id":"2601.20913","title":"Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges","created":"2026-01-28","cited_by_count":24,"area":null},{"id":"2509.06917","title":"Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents","created":"2025-09-08","cited_by_count":23,"area":null},{"id":"2601.16644","title":"Sycophancy Hides Linearly in the Attention Heads","created":"2026-01-23","cited_by_count":23,"area":null},{"id":"2505.19457","title":"BizFinBench: A Business-Driven Real-World Financial Benchmark for Evaluating LLMs","created":"2025-05-26","cited_by_count":22,"area":null},{"id":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2507.21919","title":"Training language models to be warm and empathetic makes them less reliable and more sycophantic","created":"2025-07-29","cited_by_count":21,"area":null},{"id":"2509.10147","title":"Virtual Agent Economies","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2605.05185","title":"OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents","created":"2026-05-06","cited_by_count":21,"area":null},{"id":"2506.05692","title":"SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code","created":"2025-06-06","cited_by_count":19,"area":null},{"id":"2506.13639","title":"An Empirical Study of LLM-as-a-Judge: How Design Choices Impact Evaluation Reliability","created":"2025-06-16","cited_by_count":19,"area":null},{"id":"2510.05318","title":"BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions","created":"2025-10-06","cited_by_count":19,"area":null},{"id":"2510.19032","title":"When Can We Trust LLMs in Mental Health? Large-Scale Benchmarks for Reliable LLM Evaluation","created":"2025-10-21","cited_by_count":19,"area":null},{"id":"2504.19254","title":"Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers","created":"2025-04-27","cited_by_count":18,"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":"2509.08682","title":"Automatic Failure Attribution and Critical Step Prediction Method for Multi-Agent Systems Based on Causal Inference","created":"2025-09-10","cited_by_count":18,"area":null},{"id":"2510.07550","title":"TRAVL: A Recipe for Making Video-Language Models Better Judges of Physics Implausibility","created":"2025-10-08","cited_by_count":18,"area":null},{"id":"2604.24977","title":"A Survey on LLM-based Conversational User Simulation","created":"2026-04-27","cited_by_count":18,"area":null},{"id":"2505.00662","title":"DeepCritic: Deliberate Critique with Large Language Models","created":"2025-05-01","cited_by_count":17,"area":null},{"id":"2510.06077","title":"When Thinking Drifts: Evidential Grounding for Robust Video Reasoning","created":"2025-10-07","cited_by_count":16,"area":null},{"id":"2510.11822","title":"Beyond Consensus: Mitigating the Agreeableness Bias in LLM Judge Evaluations","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2602.00521","title":"Diagnosing the Reliability of LLM-as-a-Judge via Item Response Theory","created":"2026-01-31","cited_by_count":16,"area":null},{"id":"2503.19092","title":"Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation","created":"2025-03-24","cited_by_count":15,"area":null},{"id":"2505.03427","title":"MedArabiQ: Benchmarking Large Language Models on Arabic Medical Tasks","created":"2025-05-06","cited_by_count":15,"area":null},{"id":"2510.25536","title":"TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation","created":"2025-10-29","cited_by_count":15,"area":null},{"id":"2604.00842","title":"Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants","created":"2026-04-01","cited_by_count":15,"area":null},{"id":"2504.01001","title":"Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2504.11972","title":"Reassessing Extractive QA Datasets at Scale: LLM-as-a-Judge and In-Depth Analyses","created":"2025-04-16","cited_by_count":14,"area":null},{"id":"2510.08886","title":"FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs","created":"2025-10-10","cited_by_count":14,"area":null},{"id":"2602.09383","title":"BiasScope: Towards Automated Detection of Bias in LLM-as-a-Judge Evaluation","created":"2026-02-10","cited_by_count":14,"area":null},{"id":"2412.10424","title":"LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluation","created":"2024-12-10","cited_by_count":13,"area":null},{"id":"2504.07069","title":"HalluciNot: Hallucination Detection Through Context and Common Knowledge Verification","created":"2025-04-09","cited_by_count":13,"area":null},{"id":"2506.00777","title":"Improving Automatic Evaluation of Large Language Models (LLMs) in Biomedical Relation Extraction via LLMs-as-the-Judge","created":"2025-06-01","cited_by_count":13,"area":null},{"id":"2506.10341","title":"Formalizing Learning from Language Feedback with Provable Guarantees","created":"2025-06-12","cited_by_count":13,"area":null},{"id":"2509.13813","title":"Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs","created":"2025-09-17","cited_by_count":13,"area":null},{"id":"2601.08778","title":"Pervasive Annotation Errors Break Text-to-SQL Benchmarks and Leaderboards","created":"2026-01-13","cited_by_count":13,"area":null},{"id":"2603.06865","title":"Counting on Consensus: Selecting the Right Inter-annotator Agreement Metric for NLP Annotation and Evaluation","created":"2026-03-06","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":"2503.11093","title":"OmniDiff: A Comprehensive Benchmark for Fine-grained Image Difference Captioning","created":"2025-03-14","cited_by_count":12,"area":null},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2505.19030","title":"RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data","created":"2025-05-25","cited_by_count":12,"area":null},{"id":"2509.21882","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","created":"2025-09-26","cited_by_count":12,"area":null},{"id":"2510.27172","title":"Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler","created":"2025-10-31","cited_by_count":12,"area":null},{"id":"2602.11144","title":"GENIUS: Generative Fluid Intelligence Evaluation Suite","created":"2026-02-11","cited_by_count":12,"area":null},{"id":"2604.01707","title":"Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework","created":"2026-04-02","cited_by_count":12,"area":null},{"id":"2412.09049","title":"Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues","created":"2024-12-12","cited_by_count":11,"area":null},{"id":"2503.18923","title":"Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models","created":"2025-03-24","cited_by_count":11,"area":null},{"id":"2503.24267","title":"FakeScope: Large Multimodal Expert Model for Transparent AI-Generated Image Forensics","created":"2025-03-31","cited_by_count":11,"area":null},{"id":"2504.03803","title":"What Large Language Models Do Not Talk About: An Empirical Study of Moderation and Censorship Practices","created":"2025-04-04","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":"2507.04642","title":"R1-RE: Cross-Domain Relation Extraction with RLVR","created":"2025-07-07","cited_by_count":11,"area":null},{"id":"2507.22879","title":"RecGPT Technical Report","created":"2025-07-30","cited_by_count":11,"area":null},{"id":"2509.16584","title":"From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations","created":"2025-09-20","cited_by_count":11,"area":null},{"id":"2510.04013","title":"LLM Microscope: What Model Internals Reveal About Answer Correctness and Context Utilization","created":"2025-10-05","cited_by_count":11,"area":null},{"id":"2510.08783","title":"MLLM as a UI Judge: Benchmarking Multimodal LLMs for Predicting Human Perception of User Interfaces","created":"2025-10-09","cited_by_count":11,"area":null},{"id":"2510.18560","title":"WebDevJudge: Evaluating (M)LLMs as Critiques for Web Development Quality","created":"2025-10-21","cited_by_count":11,"area":null},{"id":"2512.03042","title":"PPTArena: A Benchmark for PowerPoint Editing","created":"2025-12-02","cited_by_count":11,"area":null},{"id":"2602.06570","title":"Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Making","created":"2026-02-06","cited_by_count":11,"area":null},{"id":"2505.19236","title":"Evaluating Text Creativity across Diverse Domains: A Dataset and Large Language Model Evaluator","created":"2025-05-25","cited_by_count":10,"area":null},{"id":"2506.02672","title":"EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving","created":"2025-06-03","cited_by_count":10,"area":null},{"id":"2508.12158","title":"LLM-as-a-Judge for Privacy Evaluation? Exploring the Alignment of Human and LLM Perceptions of Privacy in Textual Data","created":"2025-08-16","cited_by_count":10,"area":null},{"id":"2508.14146","title":"MMReview: A Multidisciplinary and Multimodal Benchmark for LLM-Based Peer Review Automation","created":"2025-08-19","cited_by_count":10,"area":null},{"id":"2508.16671","title":"Reflective Paper-to-Code Reproduction Enabled by Fine-Grained Verification","created":"2025-08-21","cited_by_count":10,"area":null},{"id":"2509.21317","title":"Interactive Recommendation Agent with Active User Commands","created":"2025-09-25","cited_by_count":10,"area":null},{"id":"2509.21826","title":"ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models","created":"2025-09-26","cited_by_count":10,"area":null},{"id":"2511.18491","title":"MindEval: Benchmarking Language Models on Multi-turn Mental Health Support","created":"2025-11-23","cited_by_count":10,"area":null},{"id":"2605.09808","title":"Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants","created":"2026-05-10","cited_by_count":10,"area":null},{"id":"2501.00269","title":"A review of faithfulness metrics for hallucination assessment in Large Language Models","created":"2024-12-31","cited_by_count":9,"area":null},{"id":"2502.16706","title":"DISC: Dynamic Decomposition Improves LLM Inference Scaling","created":"2025-02-23","cited_by_count":9,"area":null},{"id":"2505.01595","title":"Always Tell Me The Odds: Fine-grained Conditional Probability Estimation","created":"2025-05-02","cited_by_count":9,"area":null},{"id":"2506.13326","title":"VIS-Shepherd: Constructing Critic for LLM-based Data Visualization Generation","created":"2025-06-16","cited_by_count":9,"area":null}],"next_cursor":"100"}