# Min-p, Max Exaggeration: A Critical Analysis of Min-p Sampling in Language Models

arXiv: https://arxiv.org/abs/2506.13681 · HTML: https://mlsanity.com/paper/2506.13681/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 16 Jun 2025.

## Builds on (most cited first, 17 of 17)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text](https://mlsanity.com/paper/2107.00061/) (2021)
- [A Careful Examination of Large Language Model Performance on Grade School Arithmetic](https://mlsanity.com/paper/2405.00332/) (2024)
- [Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs](https://mlsanity.com/paper/2407.01082/) (2024)
- [Truncation Sampling as Language Model Desmoothing](https://mlsanity.com/paper/2210.15191/) (2022)
- [Do Large Language Model Benchmarks Test Reliability?](https://mlsanity.com/paper/2502.03461/) (2025)
- [How Do Large Language Monkeys Get Their Power (Laws)?](https://mlsanity.com/paper/2502.17578/) (2025)
- [Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions](https://mlsanity.com/paper/2006.12442/) (2020)
- [Investigating Non-Transitivity in LLM-as-a-Judge](https://mlsanity.com/paper/2502.14074/) (2025)
- [Correlating and Predicting Human Evaluations of Language Models from Natural Language Processing Benchmarks](https://mlsanity.com/paper/2502.18339/) (2025)

## Built on by (most cited first, 10 of 10)

- [Position: Machine Learning Conferences Should Establish a "Refutations and Critiques" Track](https://mlsanity.com/paper/2506.19882/) (2025)
- [Pretraining Scaling Laws for Generative Evaluations of Language Models](https://mlsanity.com/paper/2509.24012/) (2025)
- [Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs](https://mlsanity.com/paper/2510.05987/) (2025)
- [Quantifying the Effect of Test Set Contamination on Generative Evaluations](https://mlsanity.com/paper/2601.04301/) (2026)
- [Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs](https://mlsanity.com/paper/2605.11128/) (2026)
- [Qrita: High-performance Top-k and Top-p using Pivot-based Truncation and Selection](https://mlsanity.com/paper/2602.01518/) (2026)
- [Adaptive Nucleus Truncation for Long-Form Reasoning](https://mlsanity.com/paper/2606.13982/) (2026)
- [Temperature Fragility and the Conditional Benefits of Truncation Sampling](https://mlsanity.com/paper/2609.15476/) (2026)
- [How Strong Is the Evidence for the Artificial Hivemind? Reevaluating Evidence for the Open-Ended Homogeneity of Language Models](https://mlsanity.com/paper/2609.33936/) (2026)
- [Truncation Samplers Are Nested: Comparing Decoding Rules Is a Measurement Problem](https://mlsanity.com/paper/2610.15570/) (2026)

## Abstract (arXiv)

Sampling from language models impacts the quality and diversity of outputs, affecting both research and real-world applications. Recently, Nguyen et al. 2024's "Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs" introduced a new sampler called min-p, claiming it achieves superior quality and diversity over established samplers such as basic, top-k, and top-p sampling. The significance of these claims was underscored by the paper's recognition as the 18th highest-scoring submission to ICLR 2025 and selection for an Oral presentation. This paper conducts a comprehensive re-examination of the evidence supporting min-p and reaches different conclusions from the original paper's four lines of evidence. First, the original paper's human evaluations omitted data, conducted statistical tests incorrectly, and described qualitative feedback inaccurately; our reanalysis demonstrates min-p did not outperform baselines in quality, diversity, or a trade-off between quality and diversity; in response to our findings, the authors of the original paper conducted a new human evaluation using a different implementation, task, and rubric that nevertheless provides further evidence min-p does not improve over baselines. Second, comprehensively sweeping the original paper's NLP benchmarks reveals min-p does not surpass baselines when controlling for the number of hyperparameters. Third, the original paper's LLM-as-a-Judge evaluations lack methodological clarity and appear inconsistently reported. Fourth, community adoption claims (49k GitHub repositories, 1.1M GitHub stars) were found to be unsubstantiated, leading to their removal; the revised adoption claim remains misleading. We conclude that evidence presented in the original paper fails to support claims that min-p improves quality, diversity, or a trade-off between quality and diversity.