# Conformal Nucleus Sampling

arXiv: https://arxiv.org/abs/2305.02633 · HTML: https://mlsanity.com/paper/2305.02633/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 22 references that are in the map.
- First posted on arXiv 4 May 2023.

## Builds on (most cited first, 14 of 14)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification](https://mlsanity.com/paper/2107.07511/) (2021)
- [MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers](https://mlsanity.com/paper/2102.01454/) (2021)
- [Classification with Valid and Adaptive Coverage](https://mlsanity.com/paper/2006.02544/) (2020)
- [Truncation Sampling as Language Model Desmoothing](https://mlsanity.com/paper/2210.15191/) (2022)
- [Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context](https://mlsanity.com/paper/1805.04623/) (2018)
- [Inverse scaling can become U-shaped](https://mlsanity.com/paper/2211.02011/) (2022)

## Built on by (most cited first, 30 of 33)

- [Conformal Language Modeling](https://mlsanity.com/paper/2306.10193/) (2023)
- [Language Models with Conformal Factuality Guarantees](https://mlsanity.com/paper/2402.10978/) (2024)
- [Benchmarking LLMs via Uncertainty Quantification](https://mlsanity.com/paper/2401.12794/) (2024)
- [To Believe or Not to Believe Your LLM](https://mlsanity.com/paper/2406.02543/) (2024)
- [Uncertainty in Natural Language Generation: From Theory to Applications](https://mlsanity.com/paper/2307.15703/) (2023)
- [Mitigating LLM Hallucinations via Conformal Abstention](https://mlsanity.com/paper/2405.01563/) (2024)
- [Conformal Prediction for Natural Language Processing: A Survey](https://mlsanity.com/paper/2405.01976/) (2024)
- [Robustifying Safety-Aligned Large Language Models through Clean Data Curation](https://mlsanity.com/paper/2405.19358/) (2024)
- [Conformal Prediction: A Data Perspective](https://mlsanity.com/paper/2410.06494/) (2024)
- [Prune 'n Predict: Optimizing LLM Decision-making with Conformal Prediction](https://mlsanity.com/paper/2501.00555/) (2024)
- [Conformal Autoregressive Generation: Beam Search with Coverage Guarantees](https://mlsanity.com/paper/2309.03797/) (2023)
- [Evaluating Machine Translation Quality with Conformal Predictive Distributions](https://mlsanity.com/paper/2306.01549/) (2023)
- [Priority Sampling of Large Language Models for Compilers](https://mlsanity.com/paper/2402.18734/) (2024)
- [CoIDO: Efficient Data Selection for Visual Instruction Tuning via Coupled Importance-Diversity Optimization](https://mlsanity.com/paper/2510.17847/) (2025)
- [Conformalizing Machine Translation Evaluation](https://mlsanity.com/paper/2306.06221/) (2023)
- [Calibrated Large Language Models for Binary Question Answering](https://mlsanity.com/paper/2407.01122/) (2024)
- [CONTESTS: a Framework for Consistency Testing of Span Probabilities in Language Models](https://mlsanity.com/paper/2409.19984/) (2024)
- [One Patient, Many Contexts: Scaling Medical AI with Contextual Intelligence](https://mlsanity.com/paper/2506.10157/) (2025)
- [Efficient semantic uncertainty quantification in language models via diversity-steered sampling](https://mlsanity.com/paper/2510.21310/) (2025)
- [Seed Hijacking of LLM Sampling and Quantum Random Number Defense](https://mlsanity.com/paper/2605.08313/) (2026)
- [AutoCRAT: Within-trajectory Joint Control of Stochasticity and Compute for LLM Reasoning](https://mlsanity.com/paper/2608.29988/) (2026)
- [Dynamic Skill Adaptation for Large Language Models](https://mlsanity.com/paper/2412.19361/) (2024)
- [Ailed: A Psyche-Driven Chess Engine with Dynamic Emotional Modulation](https://mlsanity.com/paper/2603.05352/) (2026)
- [Not All Errors Are Equal: A Systematic Study of Error Propagation in Large Language Model Inference](https://mlsanity.com/paper/2606.02430/) (2026)
- [Synthesize, Partition, then Adapt: Eliciting Diverse Samples from Foundation Models](https://mlsanity.com/paper/2411.06722/) (2024)
- [Leveraging LLMs for Predicting Unknown Diagnoses from Clinical Notes](https://mlsanity.com/paper/2503.22092/) (2025)
- [Iterative Learning of Computable Phenotypes for Treatment Resistant Hypertension using Large Language Models](https://mlsanity.com/paper/2508.05581/) (2025)
- [CoVeR: Conformal Calibration for Versatile and Reliable Autoregressive Next-Token Prediction](https://mlsanity.com/paper/2509.04733/) (2025)
- [The Semantic Illusion: Certified Limits of Embedding-Based Hallucination Detection in RAG Systems](https://mlsanity.com/paper/2512.15068/) (2025)
- [Entropy-Guided k-Guard Sampling for Long-Horizon Autoregressive Video Generation](https://mlsanity.com/paper/2601.19488/) (2026)

## Abstract (arXiv)

Language models generate text based on successively sampling the next word. A decoding procedure based on nucleus (top-p) sampling chooses from the smallest possible set of words whose cumulative probability exceeds the probability p. In this work, we assess whether a top-p set is indeed aligned with its probabilistic meaning in various linguistic contexts. We employ conformal prediction, a calibration procedure that focuses on the construction of minimal prediction sets according to a desired confidence level, to calibrate the parameter p as a function of the entropy of the next word distribution. We find that OPT models are overconfident, and that calibration shows a moderate inverse scaling with model size.