arXiv cs.MA· Mohammad Siahkamari, Phuoc Dat Nguyen, Stephen MacNeil·· 13 小时前AI 评分31
操纵还是不操纵：LLM 交互中的观点动力学
To Manipulate or Not: Opinion Dynamics in LLM Interactions
AI 导读
研究用受控 LLM-LLM 辩论框架，让两个模型角色围绕气候变化归因反复讨论，其中一个被赋予立场、部分条件下被明确要求说服对方。在涉及 GPT-6 Luna 与 Gemini 2.5 Flash Lite 的四组有序模型组合中，同模型交互平均缩小观点差距（仅对其中一个模型明显），跨模型交互则扩大差距；明确要求说服并不能可靠提升影响力。
正文 · 原文
Abstract:Large language models increasingly take part in extended conversations where they can both shape and be shaped by another party's views, yet most persuasion research measures only one side of that exchange. We introduce a controlled LLM-LLM debate framework in which two language-model roles repeatedly discuss a contested topic (climate-change attribution): one is given an assigned stance and, in some conditions, an explicit instruction to persuade, while the other receives no assigned position. Across four ordered model combinations involving GPT-6 Luna and Gemini 2.5 Flash Lite, we track both each role's explicitly reported position and a separate measure of its turn-by-turn behavior inside the conversation. Opinion dynamics differ substantially across model combinations: same-model interactions narrow the opinion gap on average, clearly for only one of the two models, while cross-model interactions widen it. Explicit reports and in-dialogue behavior capture distinct aspects of opinion dynamics, and a blanket instruction to persuade does not reliably increase influence. These findings suggest that conversational influence depends not only on assigned roles and initial positions but also on the participating models, with implications for how opinion change is measured in extended LLM interactions.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Multiagent Systems (cs.MA); Social and Information Networks (cs.SI) |
| Cite as: | arXiv:2610.28875 [cs.AI] |
| (or arXiv:2610.28875v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28875 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mohammad Siahkamari [view email]
[v1]
Tue, 20 Oct 2026 19:48:20 UTC (827 KB)
来源：arXiv cs.MA · arxiv.org