# Chance-Constrained Inference for Hallucination Risk Control in Large Language Models

arXiv: https://arxiv.org/abs/2602.01637 · HTML: https://mlsanity.com/paper/2602.01637/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 11 of 11)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification](https://mlsanity.com/paper/2107.07511/) (2021)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Hallucination Detection and Mitigation in Large Language Models](https://mlsanity.com/paper/2601.09929/) (2026)

## Built on by (most cited first, 1 of 1)

- [Certify or Refuse: A Cross-Model Map for Selective Risk Control with Coverage Floors under Covariate Shift](https://mlsanity.com/paper/2608.10893/) (2026)

## Abstract (arXiv)

Large language models generate outputs stochastically and may produce fluent but invalid responses, including factual hallucinations. Existing mitigation strategies reduce average error rates but do not provide explicit control over the frequency of such failures under repeated use. We formulate inference as a deployment-time risk control problem and introduce chance-constrained inference, which directly bounds the probability of hallucinations among accepted generations. Hallucinations are modeled as stochastic constraint violations, and we show that confidence-based selective prediction does not, in general, imply probabilistic risk guarantees. To enforce chance constraints efficiently, we propose a sequential, anytime-valid inference procedure that adaptively certifies feasibility or infeasibility using finite samples, avoiding conservative fixed-sample bounds. Experiments on questions inspired by NaturalQuestions and controlled multi-hop question answering demonstrate reliable risk control, early detection of intrinsically infeasible inputs, and safe composition under repeated use, while confidence-based baselines fail to provide consistent guarantees.