mlsanityData to 7 Oct 2026

Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs

arXiv 2407.01082 ↗First posted 1 Jul 2024cs.CLcited by 148

Not on the map. Why?

Cited by 34 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Large Language Models (LLMs) generate text by sampling the next token from a probability distribution over the vocabulary at each decoding step. Popular sampling methods like top-p (nucleus sampling) often struggle to balance quality and diversity, especially at higher temperatures which lead to incoherent or repetitive outputs. We propose min-p sampling, a dynamic truncation method that adjusts the sampling threshold based on the model's confidence by using the top token's probability as a scaling factor. Our experiments on benchmarks including GPQA, GSM8K, and AlpacaEval Creative Writing show that min-p sampling improves both the quality and diversity of generated text across different model families (Mistral and Llama 3) and model sizes (1B to 123B parameters), especially at higher temperatures. Human evaluations further show a clear preference for min-p sampling, in both text quality and creativity. Min-p sampling has been adopted by popular open-source LLM frameworks, including Hugging Face Transformers, VLLM, and many others, highlighting its considerable impact on improving text generation quality.

Key facts. Cited by 148 papers in the map (data through 7 Oct 2026). Builds on 18 of its 38 references that are in the map. First posted on arXiv 1 Jul 2024.

Builds on

18 of 38 references.

References · 18

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  5. 2018Hierarchical Neural Story Generationcited by 1,182
  6. 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 598
  7. 2017Beam Search Strategies for Neural Machine Translationcited by 232
  8. 2024Chain-of-Thought Reasoning Without Promptingcited by 208
  9. 2022Truncation Sampling as Language Model Desmoothingcited by 121
  10. 2022On Decoding Strategies for Neural Text Generatorscited by 89
  11. 2023EQ-Bench: An Emotional Intelligence Benchmark for Large Language Modelscited by 75
  12. 2023To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Reviewcited by 72
6 more
  1. 2024Confidence Regulation Neurons in Language Modelscited by 57
  2. 2024EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Samplingcited by 42
  3. 2022MAUVE Scores for Generative Models: Theory and Practicecited by 34
  4. 2023An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularizationcited by 25
  5. 2024Improving Open-Ended Text Generation via Adaptive Decodingcited by 21
  6. 2021How Optimal is Greedy Decoding for Extractive Question Answering?cited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 68; 2026: 77.

148 papers.

Sort:

By area:

  1. 2025RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learningcited by 357
  2. 2025T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scalingcited by 77
  3. 2025Generalized Interpolating Discrete Diffusioncited by 68
  4. 2025Diverse Preference Optimizationcited by 48
  5. 2025Modifying Large Language Model Post-Training for Diverse Creative Writingcited by 39
  6. 2025Weight Ensembling Improves Reasoning in Language Modelscited by 36
  7. 2025ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Codecited by 34
  8. 2025Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGIcited by 34
  9. 2025Optimizing Temperature for Language Models with Multi-Sample Inferencecited by 33
  10. 2025Training a Generally Curious Agentcited by 29
  11. 2026Maximum Likelihood Reinforcement Learningcited by 29
  12. 2025Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Rewardcited by 25
38 more
  1. 2025Diverse Preference Learning for Capabilities and Alignmentcited by 25
  2. 2025Creative Preference Optimizationcited by 24
  3. 2025Post-training Large Language Models for Diverse High-Quality Responsescited by 19
  4. 2025Representation-Based Exploration for Language Models: From Test-Time to Post-Trainingcited by 16
  5. 2025Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputscited by 15
  6. 2025Knowledge Graph-extended Retrieval Augmented Generation for Question Answeringcited by 14
  7. 2025L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Modelscited by 14
  8. 2025G2: Guided Generation for Enhanced Output Diversity in LLMscited by 14
  9. 2026TALON: Confidence-Aware Speculative Decoding with Adaptive Token Treescited by 12
  10. 2024Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-upcited by 10
  11. 2025Foundations of Top-k Decoding For Language Modelscited by 10
  12. 2025InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacycited by 10
  13. 2025GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generationcited by 10
  14. 2024Growing a Tail: Increasing Output Diversity in Large Language Modelscited by 9
  15. 2025Min-p, Max Exaggeration: A Critical Analysis of Min-p Sampling in Language Modelscited by 9
  16. 2025When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMscited by 9
  17. 2025Asking a Language Model for Diverse Responsescited by 9
  18. 2025Leak@k: Unlearning Does Not Make LLMs Forget Under Probabilistic Decodingcited by 9
  19. 2025Group-Aware Reinforcement Learning for Output Diversity in Large Language Modelscited by 9
  20. 2025Evaluating Mathematical Reasoning Across Large Language Models: A Fine-Grained Approachcited by 8
  21. 2025Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generationcited by 8
  22. 2025Optimizing Diversity and Quality through Base-Aligned Model Collaborationcited by 8
  23. 2025Bolmo: Byteifying the Next Generation of Language Modelscited by 8
  24. 2026Min-k Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamicscited by 8
  25. 2025A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMscited by 7
  26. 2025Revisiting LLMs as Zero-Shot Time-Series Forecasters: Small Noise Can Break Large Modelscited by 7
  27. 2025Position: Machine Learning Conferences Should Establish a "Refutations and Critiques" Trackcited by 7
  28. 2026Scheduling LLM Inference with Uncertainty-Aware Output Length Predictionscited by 7
  29. 2025Avoidance Decoding for Diverse Multi-Branch Story Generationcited by 6
  30. 2026ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spacescited by 6
  31. 2026Improving Sampling for Masked Diffusion Models via Information Gaincited by 6
  32. 2026Unlocking LLM Creativity in Science through Analogical Reasoningcited by 6
  33. 2025SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learningcited by 5
  34. 2025Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMscited by 5
  35. 2026Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoningcited by 5
  36. 2026Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferencescited by 5
  37. 2025Are Generative Models Underconfident? Better Quality Estimation with Boosted Model Probabilitycited by 4
  38. 2025Semantic Probabilistic Control of Language Modelscited by 4

50 most cited of 148 All 148 (JSON)