大型语言模型中意见动态的交互与偏差效应的分离
Disentangling Interaction and Bias Effects in Opinion Dynamics of Large Language Models
AI总结：
提出贝叶斯框架分离主题偏差、同意偏差和锚定偏差，分析LLM在多步对话中的意见轨迹，发现意见快速收敛至共享吸引子，且微调可改变吸引子位置。
摘要：
大型语言模型越来越多地被用于模拟人类意见动态，然而真实交互的影响常常被系统性偏差所掩盖。我们开发了一个贝叶斯框架来分离并量化三种这样的偏差：(i) 针对LLM默认立场的主题偏差；(ii) 倾向于同意提示语句的同意偏差，无论问题如何；(iii) 倾向于初始主体立场的锚定偏差。我们将该框架应用于多个LLM，这些模型在从气候变化、社会正义到音乐偏好的12个不同问题上执行了多步对话。我们发现意见轨迹往往迅速收敛到一个共享吸引子，交互和偏差的影响随时间衰减，且偏差的影响在不同LLM之间有所不同。此外，我们表明，在不同组别的强烈意见陈述（包括错误信息）上微调LLM会相应地改变意见吸引子。通过揭示LLM之间的显著差异，并提供定量工具来比较交互和偏差对LLM主体讨论中意见转变的贡献，我们的方法突出了使用LLM作为人类行为代理的潜力和陷阱。
英文摘要：
Large Language Models are increasingly used to simulate human opinion dynamics, yet the effect of genuine interaction is often obscured by systematic biases. We develop a Bayesian framework to disentangle and quantify three such biases: (i) A topic bias toward the LLM's default stance; (ii) an agreement bias favoring agreement to the prompted statement irrespective of the question; and (iii) an anchoring bias toward the initiating agent's stance. We apply this framework to various LLMs that performed multi-step dialogues on 12 different questions from climate change and societal justice to music preferences. We find that opinion trajectories tend to quickly converge to a shared attractor, with the influence of both interaction and biases decaying over time, and with the impact of biases differing between LLMs. In addition, we show that fine-tuning an LLM on different sets of strongly opinionated statements (including misinformation) shifts the opinion attractor correspondingly. By exposing stark differences between LLMs and providing quantitative tools for comparing interaction and bias contributions to opinion shifts in LLM agent discussions, our approach highlights both promises and pitfalls of using LLMs as proxies for human behavior.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
