{"total":141,"rows":[{"id":"2605.29800","title":"Nine Judges, Two Effective Votes: Correlated Errors Undermine LLM Evaluation Panels","created":"2026-05-28","cited_by_count":26,"area":null},{"id":"2605.03202","title":"Stop Automating Peer Review Without Rigorous Evaluation","created":"2026-05-04","cited_by_count":14,"area":null},{"id":"2606.14199","title":"OdysSim: Building Foundation Models for Human Behavior Simulation","created":"2026-06-12","cited_by_count":13,"area":null},{"id":"2608.19197","title":"SPADE: Self-Play in Adaptive Synthetic Executable Environments","created":"2026-08-19","cited_by_count":12,"area":"synth"},{"id":"2602.14233","title":"Evaluating LLMs in Finance Requires Explicit Bias Consideration","created":"2026-02-15","cited_by_count":11,"area":null},{"id":"2604.16027","title":"Where does output diversity collapse in post-training?","created":"2026-04-17","cited_by_count":11,"area":null},{"id":"2605.18661","title":"AI for Auto-Research: Roadmap & User Guide","created":"2026-05-18","cited_by_count":11,"area":null},{"id":"2603.11863","title":"CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges","created":"2026-03-12","cited_by_count":9,"area":null},{"id":"2604.03136","title":"StoryScope: Investigating idiosyncrasies in AI fiction","created":"2026-04-03","cited_by_count":9,"area":null},{"id":"2605.08956","title":"Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery","created":"2026-05-09","cited_by_count":8,"area":"agents"},{"id":"2603.09970","title":"CREATE: Testing LLMs for Associative Creativity","created":"2026-03-10","cited_by_count":7,"area":null},{"id":"2601.10567","title":"Generative AI collective behavior needs an interactionist paradigm","created":"2026-01-15","cited_by_count":6,"area":null},{"id":"2601.21257","title":"MoCo: A One-Stop Shop for Model Collaboration Research","created":"2026-01-29","cited_by_count":6,"area":null},{"id":"2605.11258","title":"Unlocking LLM Creativity in Science through Analogical Reasoning","created":"2026-05-11","cited_by_count":6,"area":"lr"},{"id":"2606.30571","title":"Attractor States Emerge in Multi-Turn LLM Conversations","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2608.12253","title":"One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL","created":"2026-08-12","cited_by_count":6,"area":"agents"},{"id":"2601.13518","title":"AgenticRed: Evolving Agentic Systems for Red-Teaming","created":"2026-01-20","cited_by_count":5,"area":"agents"},{"id":"2605.09995","title":"Annotations Mitigate Post-Training Mode Collapse","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2601.11227","title":"Language of Thought Shapes Output Diversity in Large Language Models","created":"2026-01-16","cited_by_count":4,"area":"lr"},{"id":"2601.22638","title":"ScholarPeer: A Context-Aware Multi-Agent Framework for Automated Peer Review","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2602.17641","title":"FAMOSE: A ReAct Approach to Automated Feature Discovery","created":"2026-02-19","cited_by_count":4,"area":null},{"id":"2603.18300","title":"Auditing Preferences for Brands and Cultures in LLMs","created":"2026-03-18","cited_by_count":4,"area":null},{"id":"2605.20506","title":"Reinforcing Human Behavior Simulation via Verbal Feedback","created":"2026-05-19","cited_by_count":4,"area":null},{"id":"2601.01530","title":"EmoHarbor: Evaluating Personalized Emotional Support by Simulating the User's Internal World","created":"2026-01-04","cited_by_count":3,"area":null},{"id":"2603.11228","title":"Markovian Generation Chains in Large Language Models","created":"2026-03-11","cited_by_count":3,"area":null},{"id":"2603.18482","title":"The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2604.08479","title":"AI generates well-liked but templatic empathic responses","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2605.20086","title":"What Do Evolutionary Coding Agents Evolve?","created":"2026-05-19","cited_by_count":3,"area":"agents"},{"id":"2607.12796","title":"The One-Word Census: Answer-Choice Conformity Across 105 Language Models","created":"2026-07-14","cited_by_count":3,"area":null},{"id":"2608.05583","title":"The Judgment-Consequence Gap: LLM Moral Reasoning in Healthcare Decisions","created":"2026-08-06","cited_by_count":3,"area":null},{"id":"2512.23601","title":"Enhancing Diversity of LLM-Generated Educational Tasks","created":"2025-12-29","cited_by_count":2,"area":null},{"id":"2601.06116","title":"The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safety","created":"2026-01-03","cited_by_count":2,"area":null},{"id":"2602.14778","title":"A Geometric Analysis of Small-sized Language Model Hallucinations","created":"2026-02-16","cited_by_count":2,"area":"agents"},{"id":"2603.14355","title":"Exposing Long-Tail Safety Failures in Large Language Models through Efficient Diverse Response Sampling","created":"2026-03-15","cited_by_count":2,"area":"alignment"},{"id":"2603.19519","title":"Inducing Sustained Creativity and Diversity in Large Language Models","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2604.02319","title":"No Single Best Model for Diversity: Learning a Router for Sample Diversity","created":"2026-04-02","cited_by_count":2,"area":null},{"id":"2605.07896","title":"What if AI systems weren't chatbots?","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2605.09918","title":"NaiAD: Initiate Data-Driven Research for LLM Advertising","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2605.11128","title":"Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2606.07812","title":"Scaling Participation in Modular AI Systems","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2606.10302","title":"Where You Inject Diversity Matters: A Unified Framework for Diverse Generation","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2606.12608","title":"Shopping Reasoning Bench: An Expert-Authored Benchmark for Multi-Turn Conversational Shopping Assistants","created":"2026-06-10","cited_by_count":2,"area":"lr"},{"id":"2606.25198","title":"Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty","created":"2026-06-23","cited_by_count":2,"area":"agents"},{"id":"2606.29985","title":"Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning","created":"2026-06-29","cited_by_count":2,"area":"lr"},{"id":"2607.01433","title":"CreativityNeuro: Steering Language Model Weights to Improve Divergent Thinking and Reduce Mode Collapse","created":"2026-07-01","cited_by_count":2,"area":"lr"},{"id":"2608.19437","title":"Are LLMs becoming similarly creative? Evidence from three years of models","created":"2026-08-19","cited_by_count":2,"area":null},{"id":"2512.25063","title":"Many Minds from One Model: Bayesian-Inspired Transformers for Population Diversity","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2601.07796","title":"Learning Through Dialogue: Engagement and Efficacy Matter More Than Explanations","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2602.00238","title":"DIVERGE: Diversity-Enhanced RAG for Open-Ended Information Seeking","created":"2026-01-30","cited_by_count":1,"area":"rag"},{"id":"2602.01689","title":"What LLMs Think When You Don't Tell Them What to Think About?","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2602.05110","title":"Understanding LLM Evaluator Behavior: A Structured Multi-Evaluator Framework for Merchant Risk Assessment","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.15327","title":"Prescriptive Scaling Reveals the Evolution of Language Model Capabilities","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2602.21317","title":"Shared Nature, Unique Nurture: PRISM for Pluralistic Reasoning via In-context Structure Modeling","created":"2026-02-24","cited_by_count":1,"area":"lr"},{"id":"2603.06870","title":"LEAD: Breaking the No-Recovery Bottleneck in Long-Horizon Reasoning","created":"2026-03-06","cited_by_count":1,"area":"lr"},{"id":"2603.25537","title":"Humans vs Vision-Language Models: A Unified Measure of Narrative Coherence","created":"2026-03-26","cited_by_count":1,"area":"mllm"},{"id":"2603.25638","title":"Beyond Via: Analysis and Estimation of the Impact of Large Language Models in Academic Papers","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2604.03472","title":"Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.11742","title":"Discourse Diversity in Multi-Turn Empathic Dialogue","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.13356","title":"Peer-Predictive Self-Training for Language Model Reasoning","created":"2026-04-14","cited_by_count":1,"area":"lr"},{"id":"2604.16755","title":"Machine individuality: Separating genuine idiosyncrasy from response bias in large language models","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2604.16757","title":"Expressing Social Emotions: Misalignment Between LLMs and Human Cultural Emotion Norms","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2604.22503","title":"How AI Writing Assistance Distorts Perceptions of AI Users and Their Opinions","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2605.27268","title":"Lost in Sampling: Assessing Lexical Reachability in LLMs via the Word Coverage Score (WCS)","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.00168","title":"RealityTest: How People Probe AI Identity and Whether Models Disclose It","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.01736","title":"Argument Collapse: LLMs Flatten Long-Form Public Debate","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.03032","title":"The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation","created":"2026-06-02","cited_by_count":1,"area":"agents"},{"id":"2606.11456","title":"AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively Vulnerable","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2606.24610","title":"Same Lesson, Different Story: Cross-Lingual Reconstruction of Cultural Narratives in Large Language Models","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2606.29933","title":"Towards Physical Intuitions for Alignment Dynamics: A Case Study With Randomness Crystallization","created":"2026-06-29","cited_by_count":1,"area":"alignment"},{"id":"2607.22554","title":"Same Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2608.11426","title":"Is Convergence Inevitable? Tracing Output Homogeneity Back to Base Models","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2608.26159","title":"Self-Generated Text Recognition: Quality Heuristics, Cross-Task Transfer, and Downstream Bias in LLM Evaluation","created":"2026-07-07","cited_by_count":1,"area":"synth"},{"id":"2609.07713","title":"The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing","created":"2026-09-07","cited_by_count":1,"area":"agents"},{"id":"2609.14896","title":"Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning","created":"2026-09-14","cited_by_count":1,"area":"alignment"},{"id":"2609.32939","title":"Theory of Scene: Breaking the Symmetry Trap in Multi-Agent LLM Coordination","created":"2026-09-26","cited_by_count":1,"area":"agents"},{"id":"2610.11966","title":"MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation","created":"2026-10-08","cited_by_count":1,"area":"lr"},{"id":"2512.12072","title":"VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2601.09084","title":"How Many Human Judgments Are Enough? Feasibility Limits of Human Preference Evaluation","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2602.09340","title":"Measuring Dataset Diversity from a Geometric Perspective","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2602.10964","title":"Can LLMs Cook Jamaican Couscous? A Study of Cultural Novelty in Recipe Generation","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2602.17377","title":"Corpus Prevalence of Multiple-Choice Question Options","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.18593","title":"Language Model Maps for Prompt-Response Distributions via Log-Likelihood Vectors","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2603.19294","title":"Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.23520","title":"From Physician Expertise to Clinical Agents: Preserving, Standardizing, and Scaling Physicians' Medical Expertise with Lightweight LLM","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2604.01504","title":"Magic, Madness, Heaven, Sin: LLM Output Diversity is Everything, Everywhere, All at Once","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.03374","title":"CresOWLve: Benchmarking Creative Problem-Solving Over Real-World Knowledge","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2605.00197","title":"The $\\textit{Silicon Society}$ Cookbook: Design Space of LLM-based Social Simulations","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.08549","title":"Evaluating Developmental Cognition Capabilities of LLMs","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.10291","title":"Generative AI Fuels Solo Entrepreneurship, but Teams Still Lead at the Top","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.00875","title":"IDEAFix: Evaluation Framework for Creative Defixation Prompting in LLMs","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.03312","title":"RobotValues: Evaluating Household Robots When Human Values Conflict","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.05985","title":"Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems","created":"2026-06-04","cited_by_count":0,"area":"agents"},{"id":"2606.07629","title":"Large Language Models Should Learn Personalized Rather Than Aggregated Human Preferences","created":"2026-05-30","cited_by_count":0,"area":"alignment"},{"id":"2606.09587","title":"Seeing the Hivemind: A Consensus-Aware Interaction Technique for Mitigating AI Homogenization","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.12790","title":"GENIE: A Fine-Grained Measure for Novelty","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.13254","title":"Evaluating Pluralism in LLMs through Latent Perspectives","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.14626","title":"Characterizing Cultural Localization in AI-Generated Stories","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.19527","title":"Emergent Alignment","created":"2026-06-17","cited_by_count":0,"area":"alignment"},{"id":"2606.24267","title":"Pigeonholing: how bad prompts hurt models, causing collapse and mistakes","created":"2026-06-23","cited_by_count":0,"area":"safety"},{"id":"2606.28343","title":"The Crowded Embedding Space: A Mean-Field Mechanism for Emergent Marginalization in Retrieval-Augmented Agents","created":"2026-06-01","cited_by_count":0,"area":"rag"}],"next_cursor":"100"}