---
title: "揭示理性：从表示定理出发的无标签评估与正则化"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.05015v1"
permalink: "https://feed.astralor.com/items/itm_d18785167f99ed01260e6411"
published: "2026-08-05T16:21:18.000Z"
score: 71
channel: "ai"
tags: ["LLM","决策理论","无标签评估","正则化","表示定理"]
---

# 揭示理性：从表示定理出发的无标签评估与正则化

## AI 点评

> 这篇论文最值得关注的是它把“理性”变成可计算的正则化信号，而不依赖人工偏好或外部标签。对做LLM对齐、评估以及AI安全方向的研究者来说，这是一个从决策理论切入的实用路径，值得细读。

## 速览

该论文提出利用决策理论中的表示定理，对大型语言模型等AI系统进行无标签评估与正则化。核心是检查模型自身对合成选择问题的回答是否满足特定公理，无需外部标签或人类反馈。作者给出三个实例：概率一致性对应德菲内蒂定理、偏好理性对应阿弗里亚特定理、主观期望效用对应Echenique-Saito定理。违规惩罚可计算，且通过检验的模型在理性意义上无法被进一步拒绝。这些惩罚补充而非替代现有评估与训练信号。

## 关键点

- 将决策理论中的表示定理应用于AI系统的无标签评估，公理合规性可从模型自身回答中检查。
- 给出三个可计算惩罚的实例：概率一致性、偏好理性与主观期望效用。
- 由于公理具有充分必要性，通过检验的模型在理性标准上无法被同一数据的进一步测试拒绝。
- 该方法作为补充信号，不替代现有评估与训练策略。

## 全文

Representation theorems in decision theory establish that behavior satisfies certain axioms if and only if it can be rationalized by a well-defined objective. I argue that this ``if and only if'' structure provides a potentially useful foundation for label-free evaluation and regularization of LLMs and other AI systems. Axiom compliance can be checked from the model's own responses to synthetic choice problems, with no external labels or human feedback, and the penalties are readily computable. Because the axioms are necessary and sufficient, the resulting checks exhaust the implications of the relevant rationality standard for the elicited data: a model that passes cannot be rejected on rationality grounds by any further test of the same data. I discuss three instantiations: probabilistic coherence via a theorem of de Finetti, preference rationality via Afriat's theorem, and subjective expected utility via a theorem of Echenique and Saito (2015), each yielding a continuous penalty that is zero whenever behavior can be rationalized. Since coherence does not restrict which objective rationalizes behavior, these penalties complement rather than replace other evaluation and training signals.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_d18785167f99ed01260e6411