{"total":84,"rows":[{"id":"2506.02314","title":"ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code","created":"2025-06-02","cited_by_count":36,"area":null},{"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":"2510.11686","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2505.17505","title":"L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models","created":"2025-05-23","cited_by_count":15,"area":null},{"id":"2510.01218","title":"Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs","created":"2025-09-20","cited_by_count":15,"area":null},{"id":"2511.00432","title":"G2: Guided Generation for Enhanced Output Diversity in LLMs","created":"2025-11-01","cited_by_count":14,"area":null},{"id":"2505.19371","title":"Foundations of Top-$k$ Decoding For Language Models","created":"2025-05-25","cited_by_count":10,"area":null},{"id":"2506.13681","title":"Min-p, Max Exaggeration: A Critical Analysis of Min-p Sampling in Language Models","created":"2025-06-16","cited_by_count":10,"area":null},{"id":"2508.20757","title":"GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation","created":"2025-08-28","cited_by_count":10,"area":null},{"id":"2511.12596","title":"Group-Aware Reinforcement Learning for Output Diversity in Large Language Models","created":"2025-11-16","cited_by_count":10,"area":null},{"id":"2411.02989","title":"Growing a Tail: Increasing Output Diversity in Large Language Models","created":"2024-11-05","cited_by_count":9,"area":null},{"id":"2509.02510","title":"Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation","created":"2025-09-02","cited_by_count":9,"area":null},{"id":"2512.15586","title":"Bolmo: Byteifying the Next Generation of Language Models","created":"2025-12-17","cited_by_count":9,"area":null},{"id":"2604.11012","title":"Min-$k$ Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics","created":"2026-04-13","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":"2604.00499","title":"Scheduling LLM Inference with Uncertainty-Aware Output Length Predictions","created":"2026-04-01","cited_by_count":8,"area":null},{"id":"2506.00457","title":"Revisiting LLMs as Zero-Shot Time-Series Forecasters: Small Noise Can Break Large Models","created":"2025-05-31","cited_by_count":7,"area":null},{"id":"2506.19882","title":"Position: Machine Learning Conferences Should Establish a \"Refutations and Critiques\" Track","created":"2025-06-24","cited_by_count":7,"area":null},{"id":"2509.02170","title":"Avoidance Decoding for Diverse Multi-Branch Story Generation","created":"2025-09-02","cited_by_count":6,"area":null},{"id":"2505.11788","title":"Communication-Efficient Hybrid Language Model via Uncertainty-Aware Opportunistic and Compressed Transmission","created":"2025-05-17","cited_by_count":5,"area":null},{"id":"2509.23234","title":"p-less Sampling: A Robust Hyperparameter-Free Approach for LLM Decoding","created":"2025-09-27","cited_by_count":5,"area":null},{"id":"2502.11115","title":"Are Generative Models Underconfident? Better Quality Estimation with Boosted Model Probability","created":"2025-02-16","cited_by_count":4,"area":null},{"id":"2505.01954","title":"Semantic Probabilistic Control of Language Models","created":"2025-05-04","cited_by_count":4,"area":null},{"id":"2508.06094","title":"ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline","created":"2025-08-08","cited_by_count":4,"area":null},{"id":"2502.14037","title":"DiffSampling: Enhancing Diversity and Accuracy in Neural Text Generation","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2602.10346","title":"Geometry-Aware Decoding with Wasserstein-Regularized Truncation and Mass Penalties for Large Language Models","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2603.09065","title":"Learning Adaptive LLM Decoding","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2603.15854","title":"FlashSampling: Fast and Memory-Efficient Exact Sampling","created":"2026-03-16","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":"2502.08436","title":"From Haystack to Needle: Label Space Reduction for Zero-shot Classification","created":"2025-02-12","cited_by_count":2,"area":null},{"id":"2504.03814","title":"Recursive Training Loops in LLMs: How training data properties modulate distribution shift in generated data?","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2507.03038","title":"Cautious Next Token Prediction","created":"2025-07-03","cited_by_count":2,"area":null},{"id":"2510.03310","title":"Predicting Effects, Missing Distributions: Evaluating LLMs as Human Behavior Simulators in Operations Management","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2512.23087","title":"Dynamic Vocabulary Pruning: Stable LLM-RL by Taming the Tail","created":"2025-12-28","cited_by_count":2,"area":null},{"id":"2602.06418","title":"Adaptive Protein Tokenization","created":"2026-02-06","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":"2604.26505","title":"Quantamination: Dynamic Quantization Leaks Your Data Across the Batch","created":"2026-04-29","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":"2605.25773","title":"Efficient Benchmarking Is Just Feature Selection and Multiple Regression","created":"2026-05-25","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":"2608.19893","title":"Interrupting the Loop: Periodic Subject Changes Raise Judged Surprise and Connection in Base Language Models","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2411.10951","title":"TSFormer: A Robust Framework for Efficient UHD Image Restoration","created":"2024-11-17","cited_by_count":1,"area":null},{"id":"2507.08870","title":"GUIDE: Towards Scalable Advising for Research Ideas","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2510.12343","title":"Traveling Salesman-Based Token Ordering Improves Stability in Homomorphically Encrypted Language Models","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2510.15061","title":"Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2602.03195","title":"Reinforcement Learning with Promising Tokens for Large Language Models","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2602.06665","title":"Not All Layers Need Tuning: Selective Layer Restoration Recovers Diversity","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.05352","title":"Ailed: A Psyche-Driven Chess Engine with Dynamic Emotional Modulation","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.07717","title":"Rigidity in LLM Bandits with Implications for Human-AI Dyads","created":"2026-03-08","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":"2605.22579","title":"Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion","created":"2026-05-21","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":"2606.13982","title":"Adaptive Nucleus Truncation for Long-Form Reasoning","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2606.22511","title":"Breaking the Likelihood Trap: Variance-Calibrated Modulation for Large Language Model Decoding","created":"2026-06-21","cited_by_count":1,"area":null},{"id":"2508.02732","title":"A Note on Code Quality Score: LLMs for Maintainable Large Codebases","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2510.18634","title":"Hardness of Learning Regular Languages in the Next Symbol Prediction Setting","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2511.05018","title":"Pluralistic Behavior Suite: Stress-Testing Multi-Turn Adherence to Custom Behavioral Policies","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2512.00789","title":"Auxiliary-Hyperparameter-Free Sampling: Entropy Equilibrium for Text Generation","created":"2025-11-30","cited_by_count":0,"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":"2601.22439","title":"Stop Jostling: Adaptive Negative Sampling Reduces the Marginalization of Low-Resource Language Tokens by Cross-Entropy Loss","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2604.03380","title":"Noise Steering for Controlled Text Generation: Improving Diversity and Reading-Level Fidelity in Arabic Educational Story Generation","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.11510","title":"Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.17244","title":"DORA Explorer: Improving the Exploration Ability of LLMs Without Training","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2604.23443","title":"Revisiting Greedy Decoding for Visual Question Answering: A Calibration Perspective","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2605.09745","title":"Entropy-informed Decoding: Adaptive Information-Driven Branching","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.10574","title":"LLM Jaggedness Unlocks Scientific Creativity","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.16538","title":"LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2606.05206","title":"Ontology-constrained multi-LLM scoring of hypothesis support in the predictive processing literature","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.22402","title":"Reinforcement learning to improve large language model-based automated code compliance systems","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2607.20791","title":"Refusal-Gated Decoding: Preserving Refusal Behavior Under High-Temperature Sampling","created":"2026-07-22","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":"2608.03233","title":"On the Diversity of Analogy Making in Large Language Models","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.22758","title":"XTC: Head-Aware Sampling by Excluding Top Choices","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.22761","title":"Don't Repeat Yourself: Stopping Verbatim Loops at Sampling Time","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.27460","title":"Accelerating LLM Inference via Vector Index Based Output Embeddings","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2609.15476","title":"Temperature Fragility and the Conditional Benefits of Truncation Sampling","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.20276","title":"Memoization Without Keys: Compact, Out-of-Core Tables for Functions of Sorted Arguments","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.27657","title":"FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation","created":"2026-09-23","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":"2609.34992","title":"Composable Decoding on the Probability Simplex: Theory and Implementation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38359","title":"Beyond Mode Collapse: Generating Diverse Synthetic Expert Conversations via Generative Flow Networks","created":"2026-09-29","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},{"id":"2610.15570","title":"Truncation Samplers Are Nested: Comparing Decoding Rules Is a Measurement Problem","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}