arXiv cs.CY· Ruben Boone, Gilles Eerlings, Sebe Vanbrabant, Davy Vanacken, Kris Luyten·· 11 小时前AI 评分31
人格提示能说服人吗？研究 LLM 的人格特质提示与说服力
Does Personality Persuade? Investigating Personality Trait Prompting and Persuasion in Large Language Models
AI 导读
研究用 IPIP-NEO-120 评估 LLM 的 Big Five 人格提示，发现提示出的人格画像可复现且能响应指定特质，但可控性因模型而异，改动一个特质会影响其他特质，未经提示的模型也呈现系统性人格画像而非中性基线。
正文 · 原文
Abstract:Large language models (LLMs) can be prompted to express different personality profiles, but it remains unclear how reliably they do so or whether personality affects their persuasiveness. We investigate these questions in two evaluations. First, we assess Big Five personality prompting using the IPIP-NEO-120, examining reproducibility, trait controllability, cross-trait effects, and unconditioned model profiles. Second, we conduct a within-subjects user study (N=32) in which participants discuss moral dilemmas with LLM agents whose personalities are aligned, mismatched, neutral, or unconditioned. We find that prompted profiles can be reproducible and responsive to requested traits, although controllability varies across models and changes to one trait can affect others. Unconditioned models also exhibit systematic personality profiles rather than neutral baselines. In the user study, personality alignment did not significantly affect perceived persuasiveness, stance switching, or confidence changes. Participants switched their initial stance in only 8 of 128 conversations, while confidence changes were more common. Participants' Big Five traits were not significantly associated with susceptibility to persuasion, but higher self-reported AI persuasion literacy was associated with less frequent confidence changes. Exploratory analysis showed that logical appeals dominated agent messages. These findings distinguish technical control over prompted LLM personality from observable influence on users and motivate evaluating persuasive interactions beyond explicit changes in decisions.
| Subjects: | Computers and Society (cs.CY) |
| Cite as: | arXiv:2611.06572 [cs.CY] |
| (or arXiv:2611.06572v1 [cs.CY] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06572 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Gilles Eerlings [view email]
[v1]
Wed, 4 Nov 2026 14:33:26 UTC (301 KB)
来源：arXiv cs.CY · arxiv.org