{"total":51,"rows":[{"id":"2509.02534","title":"Jointly Reinforcing Diversity and Quality in Language Model Generations","created":"2025-09-02","cited_by_count":80,"area":null},{"id":"2505.00047","title":"Base Models Beat Aligned Models at Randomness and Creativity","created":"2025-04-30","cited_by_count":51,"area":"alignment"},{"id":"2508.13141","title":"OptimalThinkingBench: Evaluating Over and Underthinking in LLMs","created":"2025-08-18","cited_by_count":35,"area":"lr"},{"id":"2510.20817","title":"KL-Regularized Reinforcement Learning is Designed to Mode Collapse","created":"2025-10-23","cited_by_count":31,"area":"deeprl"},{"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":"2505.14442","title":"Creative Preference Optimization","created":"2025-05-20","cited_by_count":25,"area":"alignment"},{"id":"2509.04784","title":"Post-training Large Language Models for Diverse High-Quality Responses","created":"2025-09-05","cited_by_count":19,"area":null},{"id":"2507.22168","title":"Persona-Augmented Benchmarking: Evaluating LLMs Across Diverse Writing Styles","created":"2025-07-29","cited_by_count":16,"area":null},{"id":"2506.06298","title":"Pairwise Calibrated Rewards for Pluralistic Alignment","created":"2025-05-17","cited_by_count":14,"area":"alignment"},{"id":"2604.16027","title":"Where does output diversity collapse in post-training?","created":"2026-04-17","cited_by_count":11,"area":null},{"id":"2601.09609","title":"DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing","created":"2026-01-14","cited_by_count":6,"area":"lr"},{"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":"2512.07890","title":"CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models","created":"2025-12-02","cited_by_count":5,"area":null},{"id":"2507.02804","title":"Multimodal Mathematical Reasoning with Diverse Solving Perspective","created":"2025-07-03","cited_by_count":4,"area":"lr"},{"id":"2511.19458","title":"Personalized Reward Modeling for Text-to-Image Generation","created":"2025-11-21","cited_by_count":4,"area":"alignment"},{"id":"2602.20135","title":"KNIGHT: Knowledge Graph-Driven Multiple-Choice Question Generation with Adaptive Hardness Calibration","created":"2026-02-23","cited_by_count":4,"area":"rag"},{"id":"2601.06160","title":"Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Exploration","created":"2026-01-06","cited_by_count":3,"area":"lr"},{"id":"2605.06030","title":"More Aligned, Less Diverse? Analyzing the Grammar and Lexicon of Two Generations of LLMs","created":"2026-05-07","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":"2512.16108","title":"WeMusic-Agent: Efficient Conversational Music Recommendation via Knowledge Internalization and Agentic Boundary Learning","created":"2025-12-18","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":"2602.21218","title":"EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors","created":"2026-01-31","cited_by_count":2,"area":"synth"},{"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":"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":"2606.21550","title":"AI Alignment From Social Choice Perspectives","created":"2026-06-19","cited_by_count":2,"area":"alignment"},{"id":"2505.17218","title":"Effective Reinforcement Learning for Reasoning in Language Models","created":"2025-05-22","cited_by_count":1,"area":"lr"},{"id":"2510.03515","title":"RAPID: An Efficient Reinforcement Learning Algorithm for Small Language Models","created":"2025-10-03","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":"2602.12642","title":"Beyond Normalization: Rethinking the Partition Function as a Difficulty Scheduler for RLVR","created":"2026-02-13","cited_by_count":1,"area":"lr"},{"id":"2602.15894","title":"Quality-constrained Entropy Maximization Policy Optimization for LLM Diversity","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2604.14564","title":"MARS$^2$: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2605.06540","title":"Ex Ante Evaluation of AI-Induced Idea Diversity Collapse","created":"2026-05-07","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":"2605.30150","title":"Anchorless Diversification for Parallel LLM Ideation","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.17350","title":"Do Large Language Models Always Tell The Same Stories?","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2607.03174","title":"Effectiveness of LLM-based Software Diversity for Reliability Improvement -- an Empirical Study","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2607.19848","title":"emb-diversity: A Tool for Embedding-Based Measurement of Data Diversity","created":"2026-07-22","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":"2609.00683","title":"Creative Generation via Multi-Agent Debate: Does Debate Suppress Diversity?","created":"2026-09-01","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":"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":"2605.29190","title":"When RL Suppresses Its Own Vocabulary: Recovering Reasoning Diversity in Puzzle-to-Math Transfer","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2606.15521","title":"Emergent retokenization symmetry in large language models: phenomenology and applications","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2608.24228","title":"Evaluating Multiple LLM Generations with Validated Task Coverage","created":"2026-08-25","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":"2609.31571","title":"Strategically Diverse Sampling for Self-Training","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"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":"2609.38805","title":"Explicit Trajectory Diversity for RL-Based Post-Training of LLM Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.01382","title":"Gacha Decoding: Eliciting Diverse Generations Through Instruction Following","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}],"next_cursor":null}