arXiv cs.CL· Senthil Rajasekaran, Stylianos Loukas Vasileiou·· 11 小时前AI 评分31
前沿大语言模型中的 Asch 从众效应：一种定量研究方法
A Quantitative Approach to Asch Conformity in Frontier Large Language Models
AI 导读
研究提出对前沿 LLM 的 Asch 从众效应做定量分析：不再对一组问题各采样一次，而是对同一问题重复采样，利用模型输出的概率性得到答案分布，再比较模型在被告知“人造共识”前后的分布变化。实验确认前沿 LLM 确实会从众，并通过分布对分布的对比，给出导致从众的条件及其程度的额外定量数据。
正文 · 原文
Abstract:The Asch conformity experiment has recently gained considerable attention as a way of measuring conformity in large language models (LLMs). While previous studies have focused on demonstrating conformity in LLMs, our work adds a further quantitative layer to this approach. Instead of sampling a frontier LLM on a suite of questions, our approach samples a single question repeatedly, leveraging the probabilistic nature of LLMs to produce a distribution of answers. In doing so, we can compare the distributions of answers before and after the model is presented with the manufactured consensus. Our experiments confirm that frontier LLMs do conform, reinforcing prior literature, and, through our distribution-to-distribution comparisons, provide additional quantitative data on the conditions that lead to conformity and the degree to which it occurs.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.36668 [cs.CL] |
| (or arXiv:2610.36668v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36668 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Stylianos Loukas Vasileiou [view email]
[v1]
Tue, 27 Oct 2026 05:40:08 UTC (133 KB)
来源：arXiv cs.CL · arxiv.org