{"total":51,"rows":[{"id":"2510.20817","title":"KL-Regularized Reinforcement Learning is Designed to Mode Collapse","created":"2025-10-23","cited_by_count":31,"area":"deeprl"},{"id":"2506.17871","title":"LLM Probability Concentration: How Alignment Shrinks the Generative Horizon","created":"2025-06-22","cited_by_count":26,"area":"alignment"},{"id":"2505.14442","title":"Creative Preference Optimization","created":"2025-05-20","cited_by_count":25,"area":"alignment"},{"id":"2603.23231","title":"PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments","created":"2026-03-24","cited_by_count":14,"area":"agents"},{"id":"2605.03202","title":"Stop Automating Peer Review Without Rigorous Evaluation","created":"2026-05-04","cited_by_count":14,"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":"2505.19184","title":"When Two LLMs Debate, Both Think They'll Win","created":"2025-05-25","cited_by_count":10,"area":"lr"},{"id":"2510.09913","title":"Don't Throw Away Your Pretrained Model","created":"2025-10-10","cited_by_count":10,"area":"lr"},{"id":"2505.16245","title":"Diverse, not Short: A Length-Controlled Data Selection Strategy for Improving Response Diversity of Language Models","created":"2025-05-22","cited_by_count":9,"area":null},{"id":"2511.05650","title":"Optimizing Diversity and Quality through Base-Aligned Model Collaboration","created":"2025-11-07","cited_by_count":8,"area":null},{"id":"2603.09970","title":"CREATE: Testing LLMs for Associative Creativity","created":"2026-03-10","cited_by_count":7,"area":null},{"id":"2603.24844","title":"Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models","created":"2026-03-25","cited_by_count":6,"area":"lr"},{"id":"2605.11258","title":"Unlocking LLM Creativity in Science through Analogical Reasoning","created":"2026-05-11","cited_by_count":6,"area":"lr"},{"id":"2605.09995","title":"Annotations Mitigate Post-Training Mode Collapse","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2602.16162","title":"LLMs Exhibit Significantly Lower Uncertainty in Creative Writing Than Professional Writers","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2506.20666","title":"Cognitive models can reveal interpretable value trade-offs in language models","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2601.21339","title":"Within-Model vs Between-Prompt Variability in Large Language Models for Creative Tasks","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2510.12699","title":"Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations","created":"2025-10-14","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":"2603.18363","title":"PowerFlow: Unlocking the Dual Nature of LLMs via Principled Distribution Matching","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":"2605.11128","title":"Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2606.03962","title":"Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning","created":"2026-06-02","cited_by_count":2,"area":"alignment"},{"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":"2505.17218","title":"Effective Reinforcement Learning for Reasoning in Language Models","created":"2025-05-22","cited_by_count":1,"area":"lr"},{"id":"2507.15736","title":"IDRBench: Understanding the Capability of Large Language Models on Interdisciplinary Research","created":"2025-07-21","cited_by_count":1,"area":null},{"id":"2511.01490","title":"Synthetic Eggs in Many Baskets: The Impact of Synthetic Data Diversity on LLM Fine-Tuning","created":"2025-11-03","cited_by_count":1,"area":"synth"},{"id":"2601.17865","title":"D-Models and E-Models: Diversity-Stability Trade-offs in the Sampling Behavior of Large Language Models","created":"2026-01-25","cited_by_count":1,"area":null},{"id":"2604.11840","title":"Diversity Without Fidelity: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation Simulation","created":"2026-04-12","cited_by_count":1,"area":"agents"},{"id":"2605.10794","title":"Can You Keep a Secret? Involuntary Information Leakage in Language Model Writing","created":"2026-05-11","cited_by_count":1,"area":"lr"},{"id":"2605.27878","title":"Narrative Flattening: How Post-Training Compresses Thematic, Affective, and Stylistic Variation in LLM Fiction","created":"2026-05-27","cited_by_count":1,"area":null},{"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":"2606.29933","title":"Towards Physical Intuitions for Alignment Dynamics: A Case Study With Randomness Crystallization","created":"2026-06-29","cited_by_count":1,"area":"alignment"},{"id":"2608.11426","title":"Is Convergence Inevitable? Tracing Output Homogeneity Back to Base Models","created":"2026-08-11","cited_by_count":1,"area":null},{"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":"2510.03527","title":"Sample, Align, Synthesize: Graph-Based Response Synthesis with ConGrs","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2604.11522","title":"Triviality Corrected Endogenous Reward","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.28664","title":"Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection","created":"2026-05-27","cited_by_count":0,"area":"mechinterp"},{"id":"2605.30844","title":"Fine-Tuning Improves Information Conveyance in Language Models","created":"2026-05-29","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":"2606.12790","title":"GENIE: A Fine-Grained Measure for Novelty","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.01849","title":"Decomposer: Learning to Decompile Symbolic Music to Programs","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.05726","title":"Mitigating Scoring Bias in LLM-as-a-Judge via Random Number Generation","created":"2026-08-06","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":"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":"2609.34929","title":"Sample What You Say: Aligning Language Models to Sample the Distributions They State","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2610.01382","title":"Gacha Decoding: Eliciting Diverse Generations Through Instruction Following","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.03529","title":"Divergence controls entropy in distillation","created":"2026-10-02","cited_by_count":0,"area":"distill"},{"id":"2610.11539","title":"Design Creativity Bench: Measuring creativity in LLM-Generated UI","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.12998","title":"Evaluating LLM Creativity through Long-Tail Performance","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}