{"total":100,"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":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"id":"2504.14225","title":"Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale","created":"2025-04-19","cited_by_count":178,"area":null},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"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":"2510.06552","title":"Flipping the Dialogue: Training and Evaluating User Language Models","created":"2025-10-08","cited_by_count":58,"area":null},{"id":"2510.17516","title":"SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors","created":"2025-10-20","cited_by_count":52,"area":null},{"id":"2504.14439","title":"LoRe: Personalizing LLMs via Low-Rank Reward Modeling","created":"2025-04-20","cited_by_count":38,"area":"alignment"},{"id":"2502.20897","title":"Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptions","created":"2025-02-28","cited_by_count":33,"area":null},{"id":"2409.11239","title":"LLM-as-a-Judge & Reward Model: What They Can and Cannot Do","created":"2024-09-17","cited_by_count":32,"area":"alignment"},{"id":"2503.06358","title":"Language Model Personalization via Reward Factorization","created":"2025-03-08","cited_by_count":31,"area":"alignment"},{"id":"2506.05598","title":"SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs","created":"2025-06-05","cited_by_count":29,"area":"alignment"},{"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":"2504.10147","title":"A Survey of Personalization: From RAG to Agent","created":"2025-04-14","cited_by_count":27,"area":"rag"},{"id":"2501.14956","title":"ExPerT: Effective and Explainable Evaluation of Personalized Long-Form Text Generation","created":"2025-01-24","cited_by_count":26,"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":"2410.16027","title":"ComPO: Community Preferences for Language Model Personalization","created":"2024-10-21","cited_by_count":19,"area":"alignment"},{"id":"2503.00596","title":"BadJudge: Backdoor Vulnerabilities of LLM-as-a-Judge","created":"2025-03-01","cited_by_count":18,"area":"safety"},{"id":"2510.16282","title":"Instant Personalized Large Language Model Adaptation via Hypernetwork","created":"2025-10-18","cited_by_count":18,"area":null},{"id":"2502.16182","title":"IPO: Your Language Model is Secretly a Preference Classifier","created":"2025-02-22","cited_by_count":17,"area":"alignment"},{"id":"2407.13244","title":"PM-LLM-Benchmark: Evaluating Large Language Models on Process Mining Tasks","created":"2024-07-18","cited_by_count":16,"area":null},{"id":"2504.02953","title":"Cultural Learning-Based Culture Adaptation of Language Models","created":"2025-04-03","cited_by_count":16,"area":null},{"id":"2508.03550","title":"Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations","created":"2025-08-05","cited_by_count":15,"area":"alignment"},{"id":"2412.14140","title":"GLIDER: Grading LLM Interactions and Decisions using Explainable Ranking","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2507.10587","title":"Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing","created":"2025-07-11","cited_by_count":14,"area":null},{"id":"2601.02179","title":"Confidence Estimation for LLMs in Multi-turn Interactions","created":"2026-01-05","cited_by_count":12,"area":null},{"id":"2504.12663","title":"Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment","created":"2025-04-17","cited_by_count":11,"area":"alignment"},{"id":"2505.11613","title":"MedGUIDE: Benchmarking Clinical Decision-Making in Large Language Models","created":"2025-05-16","cited_by_count":10,"area":null},{"id":"2502.19158","title":"When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning","created":"2025-02-26","cited_by_count":9,"area":"alignment"},{"id":"2504.04934","title":"Boosting Relational Deep Learning with Pretrained Tabular Models","created":"2025-04-07","cited_by_count":9,"area":null},{"id":"2504.20094","title":"Toward Safe and Human-Aligned Game Conversational Recommendation via Multi-Agent Decomposition","created":"2025-04-26","cited_by_count":9,"area":"agents"},{"id":"2508.07805","title":"Can You Trick the Grader? Adversarial Persuasion of LLM Judges","created":"2025-08-11","cited_by_count":9,"area":null},{"id":"2507.21134","title":"TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law","created":"2025-07-22","cited_by_count":8,"area":"safety"},{"id":"2509.22957","title":"Doubly-Robust LLM-as-a-Judge: Externally Valid Estimation with Imperfect Personas","created":"2025-09-26","cited_by_count":8,"area":null},{"id":"2504.02867","title":"Multi-Agent LLM Judge: automatic personalized LLM judge design for evaluating natural language generation applications","created":"2025-04-01","cited_by_count":7,"area":"agents"},{"id":"2502.12149","title":"HARBOR: Exploring Persona Dynamics in Multi-Agent Competition","created":"2025-02-17","cited_by_count":6,"area":"agents"},{"id":"2503.23243","title":"Evaluating how LLM annotations represent diverse views on contentious topics","created":"2025-03-29","cited_by_count":6,"area":null},{"id":"2506.10491","title":"Surface Fairness, Deep Bias: A Comparative Study of Bias in Language Models","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":"2601.18777","title":"PRECISE: Reducing the Bias of LLM Evaluations Using Prediction-Powered Ranking Estimation","created":"2026-01-26","cited_by_count":6,"area":"rag"},{"id":"2409.16973","title":"Adaptive Self-Supervised Learning Strategies for Dynamic On-Device LLM Personalization","created":"2024-09-25","cited_by_count":5,"area":null},{"id":"2509.21791","title":"Quantifying the Impact of Structured Output Format on Large Language Models through Causal Inference","created":"2025-09-26","cited_by_count":5,"area":null},{"id":"2510.13501","title":"Confidence as a Reward: Transforming LLMs into Reward Models","created":"2025-10-15","cited_by_count":5,"area":"lr"},{"id":"2512.07890","title":"CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models","created":"2025-12-02","cited_by_count":5,"area":null},{"id":"2605.20767","title":"The Illusion of Intervention: Your LLM-Simulated Experiment is an Observational Study","created":"2026-05-20","cited_by_count":5,"area":null},{"id":"2503.03335","title":"iNews: A Multimodal Dataset for Modeling Personalized Affective Responses to News","created":"2025-03-05","cited_by_count":4,"area":null},{"id":"2604.12479","title":"Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning","created":"2026-04-14","cited_by_count":4,"area":"alignment"},{"id":"2411.08506","title":"Towards Operationalizing Right to Data Protection","created":"2024-11-13","cited_by_count":3,"area":null},{"id":"2505.24539","title":"Localizing Persona Representations in LLMs","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2507.07787","title":"Measuring AI Alignment with Human Flourishing","created":"2025-07-10","cited_by_count":3,"area":null},{"id":"2501.12651","title":"The potential -- and the pitfalls -- of using pre-trained language models as cognitive science theories","created":"2025-01-22","cited_by_count":2,"area":null},{"id":"2503.08035","title":"Group Preference Alignment: Customized LLM Response Generation from In-Situ Conversations","created":"2025-03-11","cited_by_count":2,"area":"alignment"},{"id":"2503.16457","title":"Integrating Personality into Digital Humans: A Review of LLM-Driven Approaches for Virtual Reality","created":"2025-02-22","cited_by_count":2,"area":null},{"id":"2507.00439","title":"Improving the Distributional Alignment of LLMs using Supervision","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2511.04478","title":"Generate, Evaluate, Iterate: Synthetic Data for Human-in-the-Loop Refinement of LLM Judges","created":"2025-11-06","cited_by_count":2,"area":"synth"},{"id":"2601.06403","title":"Steer Model beyond Assistant: Controlling System Prompt Strength via Contrastive Decoding","created":"2026-01-10","cited_by_count":2,"area":null},{"id":"2502.20635","title":"Can LLM Assist in the Evaluation of the Quality of Machine Learning Explanations?","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2505.13257","title":"Is Active Persona Inference Necessary for Aligning Small Models to Personal Preferences?","created":"2025-05-19","cited_by_count":1,"area":"alignment"},{"id":"2505.22777","title":"MEDAL: A Framework for Benchmarking LLMs as Multilingual Open-Domain Dialogue Evaluators","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.04019","title":"CETBench: A Novel Dataset constructed via Transformations over Programs for Benchmarking LLMs for Code-Equivalence Checking","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2506.05748","title":"Efficient Online RFT with Plug-and-Play LLM Judges: Unlocking State-of-the-Art Performance","created":"2025-06-06","cited_by_count":1,"area":"alignment"},{"id":"2506.08593","title":"Hateful Person or Hateful Model? Investigating the Role of Personas in Hate Speech Detection by Large Language Models","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2508.10161","title":"LaajMeter: A Framework for LaaJ Evaluation","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2511.01932","title":"Deciphering Personalization: Towards Fine-Grained Explainability in Natural Language for Personalized Image Generation Models","created":"2025-11-02","cited_by_count":1,"area":null},{"id":"2511.04366","title":"Towards Aligning Multimodal LLMs with Human Experts: A Focus on Parent-Child Interaction","created":"2025-11-06","cited_by_count":1,"area":"mllm"},{"id":"2512.16532","title":"From Personalization to Prejudice: Bias and Discrimination in Memory-Enhanced AI Agents for Recruitment","created":"2025-12-18","cited_by_count":1,"area":"agents"},{"id":"2601.22570","title":"Leveraging Data to Say No: Memory Augmented Plug-and-Play Selective Prediction","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2603.21404","title":"Multi-Perspective LLM Annotations for Valid Analyses in Subjective Tasks","created":"2026-03-22","cited_by_count":1,"area":null},{"id":"2604.14773","title":"CoPA: Benchmarking Personalized Question Answering with Data-Informed Cognitive Factors","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2606.06614","title":"Re-Centering Humans in LLM Personalization","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2608.29455","title":"Item-Mean Surrogates: Why Richer Persona Data Fail to Improve LLMs as Human Surrogates","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2502.13396","title":"Prompting a Weighting Mechanism into LLM-as-a-Judge in Two-Step: A Case Study","created":"2025-02-19","cited_by_count":0,"area":null},{"id":"2505.20451","title":"Amulet: Putting Complex Multi-Turn Conversations on the Stand with LLM Juries","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2508.07178","title":"Improved Personalized Headline Generation via Denoising Fake Interests from Implicit Feedback","created":"2025-08-10","cited_by_count":0,"area":null},{"id":"2508.11434","title":"Online Anti-sexist Speech: Identifying Resistance to Gender Bias in Political Discourse","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2509.14132","title":"When Avatars Have Personality: Effects on Engagement and Communication in Immersive Medical Training","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2509.21562","title":"Comparative Personalization for Multi-document Summarization","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2510.01976","title":"Taking a SEAT: Predicting Value Interpretations from Sentiment, Emotion, Argument, and Topic Annotations","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2512.16019","title":"Few-Shot Inference of Human Perceptions of Robot Performance in Social Navigation Scenarios","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2601.16987","title":"Evaluating Reward Model Generalization via Pairwise Maximum Discrepancy Competitions","created":"2026-01-05","cited_by_count":0,"area":"alignment"},{"id":"2603.28351","title":"Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.09876","title":"Efficient Personalization of Generative User Interfaces","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.22517","title":"Aggregate vs. Personalized Judges in Business Idea Evaluation: Evidence from Expert Disagreement","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.10367","title":"AgentGR: Semantic-aware Agentic Group Decision-Making Simulator for Group Recommendation","created":"2026-05-11","cited_by_count":0,"area":"agents"},{"id":"2605.18805","title":"RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents","created":"2026-05-11","cited_by_count":0,"area":"agents"},{"id":"2605.27395","title":"Informing AI Policy Assessment using Large-Scale Simulation of Interventions","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.29711","title":"Personalized Turn-Level User Conversation Satisfaction Benchmark","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.03189","title":"SenseJudge: Human-Centric Preference-Driven Judgment Framework","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.16368","title":"Evaluating LLM Personalization via Semantic Constraint Verification","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.17506","title":"Evaluating Second-Order Bias of LLMs Through Epistemic Entitlement","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.25361","title":"Memory Makes the Difference: Evaluating How Different Memory Roles Shape Conversational Agents","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2607.00937","title":"Persona Non Grata: LLM Persona-Driven Generations in MCQA are Unstable in Distinct Dimensions","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.26180","title":"PACEShop: Evaluating Personalized, Actionable, Compositional, and Evidence-grounded Shopping Assistants","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.00014","title":"Behaviorally Grounded User Profiles from the Wild for Personalized Alignment and Multi-Perspective Reasoning","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2609.00222","title":"LLM-as-a-Demographic: Whom Sociodemographic Prompting Helps, and Whom It Hurts","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.09835","title":"HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization","created":"2026-09-09","cited_by_count":0,"area":"alignment"},{"id":"2609.22112","title":"Privacy Personalization Trade offs in LLMs: The Impact of Stylometric Signal Reduction on User-Specific Text Generation","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2609.30290","title":"Auditing and Repairing LLM-as-Judge Failures in a Production Text-to-SQL Pipeline","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2610.19314","title":"PersEvalBench: Can LLM Evaluators Judge Contextually Appropriate Use of Persona Information?","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}