{"total":97,"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":"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":"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":"2606.30571","title":"Attractor States Emerge in Multi-Turn LLM Conversations","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2605.09995","title":"Annotations Mitigate Post-Training Mode Collapse","created":"2026-05-11","cited_by_count":5,"area":null},{"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":"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":"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":"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":"2602.05110","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":"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":"2604.16755","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":"2606.24610","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":"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":"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":"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":"2606.09587","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":"2607.02368","title":"Beyond Cultural Persona Bias: Response Geometry as a Measure for Language Models and People","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.13077","title":"The Hitchhiker's Guide to Monoculture: AI Homogenizes Syntax, Not (Necessarily) Semantics","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.18476","title":"Structured Output Collapses Answer Diversity Across 44 Language Models","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.20429","title":"More Is Not More: What Matters for Diversity in LLM Opinions?","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2607.26899","title":"Human diversity fuels collective creativity that large language models cannot simulate or sustain","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.00410","title":"Where did the ambiguity go? Examining how multimodal models interpret polysemous words","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.02618","title":"Beyond the Hivemind: Escaping LLM Homogeneity via Meta-Persona Anchoring and Sequential Temperature Scaling","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2608.07460","title":"CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversity","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.30345","title":"Answer Probing-Guided Search for Diverse Solution Exploration of LLMs","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.03422","title":"Inferred Generative-Process Diversity Predicts Correlated Failure Across Language Models","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.04141","title":"Efficient Test-Time Adaptation through Human-AI Interaction","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.04835","title":"On Epistemic Diversity in Large Language Models","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.09901","title":"Deep and shallow biases in language models","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.10758","title":"Multilingual in Name Only? Cultural and Linguistic Weaknesses of LLMs in Urdu","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.16051","title":"\"Looking for Something Weird to Happen\": How Humans Sustain AI Agent Novelty Amid Semantic Collapse","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.16667","title":"ANIMASK: What the Model Contributes to Role Play in Simulated Story Worlds","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.22152","title":"Is Imagination Derived from Hallucination? A Cross-Taxonomy Evaluation of Imagination and Hallucination in Large Language Models","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.22607","title":"Pretrained Persona Mixture Models and Tandem Models for Human Simulation","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.30492","title":"Breaking Homogeneity: Diversifying Persona Sets for Creative LLM Outputs","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.33936","title":"How Strong Is the Evidence for the Artificial Hivemind? Reevaluating Evidence for the Open-Ended Homogeneity of Language Models","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35302","title":"Narrowing the Horizon: Quantifying Topic Saliency Shifts in Generative Monoculture","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38448","title":"Reach Into The CHOIR: Free-List Elicitation Uncovers Distinct Model Voices in LLM Ensembles","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39229","title":"RAIM: Robust Aggregation of Inexpensive Models for Hallucination Detection","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39483","title":"Who Owns That? Evaluating Ownership Intuitions in Large Language Models","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00707","title":"Initialization Improves LLM-Driven Discovery","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01382","title":"Gacha Decoding: Eliciting Diverse Generations Through Instruction Following","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.01661","title":"DiVid: Diagnosing Dimension-Specific Diversity Collapse in Video Generation Models","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.11539","title":"Design Creativity Bench: Measuring creativity in LLM-Generated UI","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.14031","title":"PLDiv: Measuring Dataset Diversity and Semantic Collapse via Persistence Landscapes","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.20162","title":"Gap Detection: Mitigating Homogenization through Demand and Defensibility","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}