---
title: "超越谄媚：LLM道德推理中的结构化抵抗与顺从"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.21558v1"
permalink: "https://feed.astralor.com/items/itm_dcb622af86bf72eb28823477"
published: "2026-07-23T17:40:07.000Z"
score: 72
channel: "tech"
tags: ["AI对齐","大型语言模型","社会影响","谄媚"]
---

# 超越谄媚：LLM道德推理中的结构化抵抗与顺从

## AI 点评

> 这篇论文巧妙地将社会心理学中的经典现象映射到LLM行为分析中，重新定义了“谄媚”问题，值得所有关注AI对齐和模型社会性的读者细读。它提示我们，模型在道德推理中的“顺从”并非单纯缺陷，而是一个复杂的结构化过程，对设计更安全的AI系统有启发意义。

## 速览

该研究提出，大型语言模型（LLM）在道德推理中的判断修订并非简单的谄媚失败，而是沿三个维度结构化：与初始立场的距离、观点来源归属以及支持该观点的联盟结构。模型对邻近立场更开放、更受自身先前判断影响、并对群体压力有差异化响应。这一框架为区分建设性信念修正与谄媚顺从提供了原则性基础，有助于改进对齐。

## 关键点

- LLM的道德判断修订沿距离、来源归属和联盟结构三个维度结构化。
- 模型对邻近立场更开放，更受自身先前判断影响，对群体压力有不同响应。
- 该框架将谄媚重新定义为更广泛社会影响过程的特例。
- 为建设性信念修正与顺从的区分提供了原则性依据。

## 全文

Building socially calibrated large language models, which can learn from others without simply yielding to them, requires more than reducing sycophancy as a one-dimensional failure mode. Models must distinguish when to incorporate others' perspectives from when to maintain a well-grounded moral judgment. We study the broader resistance-compliance process governing this distinction. Across three studies, we show that models' judgment revision is structured along three dimensions that parallel classic phenomena in human social psychology: the distance between an incoming view and the model's initial position, the source attribution of that view, and the coalition structure supporting it. Models are generally more receptive to nearby positions, more influenced by views presented as their own prior judgments, and differently responsive to group pressure. These findings recast sycophancy as one expression of a broader judgment-updating process shaped by social influence. Our framework provides a principled basis for distinguishing constructive belief revision from sycophantic compliance, thereby supporting better alignment in morally consequential interactions.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_dcb622af86bf72eb28823477