---
title: "基于推理介导行为模型的LLM社会模拟器审计方法"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.24649v1"
permalink: "https://feed.astralor.com/items/itm_adfe8fb8307f258931b10811"
published: "2026-07-27T16:47:27.000Z"
score: 79
channel: "tech"
tags: ["人工智能评估","大型语言模型","推理审计","社会模拟器","行为模型"]
---

# 基于推理介导行为模型的LLM社会模拟器审计方法

## AI 点评

> 这篇论文切中了当前LLM社会模拟器评估中一个被忽视的痛点：我们太容易满足于答案的相似性，却忽略了推理模型的系统性偏差。对于从事AI社会科学应用、合成数据生成以及可解释AI的从业者来说，这种审计框架能帮助识别那些看似合理但实际走捷径的模拟器。个人认为，将推理状态作为“可解释性指标”是向正确方向迈出的重要一步。

## 速览

大型语言模型被广泛用作社会模拟器（如合成调查受访者）。现有评估多关注模拟结果是否匹配人类答案，但忽略了推理路径的合理性。本研究通过94人的防晒产品概念测试，将人类开放性理由映射为带符号的推理状态，证明基于人类推理的状态能显著提升购买意向预测，而LLM模拟的推理虽表面合理却常重复概念板内容，未能还原受访者的接受或拒绝路径。论文提出了一种可解释的审计框架，用于检验模拟器的推理是否与人类证据一致。

## 关键点

- 提出基于推理状态（Reason State）的审计方法，将人类开放性理由编码为带符号的二元状态，用于评估LLM社会模拟器的推理一致性。
- 通过94人防晒产品概念测试发现，人类推理状态能显著提升购买意向预测，而LLM模拟的推理虽表面合理但常偏离真实决策路径。
- 该框架不要求识别因果效应，但提供了可解释的检验标准，用于判断模拟器的推理是否与人类证据匹配。

## 全文

Large language models are increasingly used as social simulators, including as synthetic survey respondents. Most evaluations ask whether simulated outcomes resemble human outcomes. We argue that this is necessary but too weak: a simulator can match the final answer while using the wrong rationale-derived reason pattern. We study this problem through a 94-person sunscreen concept test in which each respondent evaluated three product concepts and wrote open-ended rationales. We map those rationales into signed reason states $Z$, where positive signs support adoption and negative signs block it. This gives a practical audit: holding respondent descriptors $D$, category context $K$, and concept treatment $X$ fixed, do human rationale-derived reasons help predict behavior $Y$, and can an LLM simulate the same reason state without seeing the human rationale or outcome? Human rationale-derived reasons substantially improve held-out prediction of purchase intent. LLM-simulated reasons are more brittle: they often sound plausible, but frequently echo the concept board rather than recover the respondent's acceptance or rejection path. The paper contributes an evaluation framework for social simulators. Reason states do not identify natural causal effects by themselves, but they provide an interpretable test of whether a simulator's stated reasons align with human evidence.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_adfe8fb8307f258931b10811