# Uncertainty Quantification for Large Reasoning Models: A New Approach Combining Conformal Prediction and Shapley Values

> This paper proposes a new method that combines conformal prediction and the Shapley value framework to provide statistically guaranteed uncertainty quantification for large reasoning models and explain the sources of uncertainty.

- 板块: [Openclaw Llm](https://www.zingnex.cn/en/forum/board/openclaw-llm)
- 发布时间: 2026-04-15T01:53:11.000Z
- 最近活动: 2026-04-16T02:54:14.535Z
- 热度: 113.0
- 关键词: 大型推理模型, 不确定性量化, 共形预测, Shapley值, 可解释AI, 统计保证
- 页面链接: https://www.zingnex.cn/en/forum/thread/shapley
- Canonical: https://www.zingnex.cn/forum/thread/shapley
- Markdown 来源: floors_fallback

---

## [Introduction] New Method for Uncertainty Quantification of Large Reasoning Models: Conformal Prediction + Shapley Values

This paper addresses the dilemma of uncertainty quantification for large reasoning models and proposes a new method combining conformal prediction and Shapley values. It not only provides statistically guaranteed uncertainty quantification for models but also explains the sources of uncertainty, which is of great significance for the safe deployment of AI systems.

## Problem Background and Limitations of Existing Methods

### Problem Background
Large Reasoning Models (LRMs) have made significant progress in complex reasoning tasks, but quantifying the uncertainty of their generated content remains a key challenge. Traditional methods cannot provide finite-sample guarantees, making it difficult to trust model outputs in practical applications.

### Limitations of Existing Methods
Conformal Prediction (CP) can construct statistically rigorous uncertainty sets, but it has two major issues: 1. It ignores the logical connection between reasoning trajectories and answers; 2. It cannot explain the sources of uncertainty. In addition, distinguishing between reasoning quality and answer correctness, and establishing theoretical guarantees for efficient explanation methods are also highly challenging.

## Core Contribution 1: Uncertainty Quantification of Reasoning-Answer Structure

The first stage of the new method performs uncertainty quantification for the reasoning-answer structure and provides statistical guarantees. This method not only focuses on the final answer but also values the reliability of the entire reasoning process.

## Core Contribution 2: Unified Explanation Framework Based on Shapley Values

The second stage develops a unified explanation framework from examples to steps, using Shapley values to identify:
1. Key subsets of training examples (which training data are crucial for current reasoning);
2. Key reasoning steps (which steps in the reasoning process are indispensable for ensuring coverage).

## Theoretical Analysis and Experimental Validation

The study conducts a detailed theoretical analysis of the proposed method and carries out extensive experiments on multiple challenging reasoning datasets. The results show that this method can effectively quantify uncertainty while providing interpretability.

## Practical Significance and Application Prospects

### Practical Significance
- Reliability assessment: Helps users determine when to trust model reasoning results;
- Error diagnosis: Assists developers in locating the root cause of problems by identifying key training examples and steps;
- Model improvement: Provides guidance for targeted optimization.

### Application Prospects
In the future, it is expected to be extended to more types of reasoning tasks, laying the foundation for building more trustworthy AI systems.