用插值解码让大模型模拟人格连续变化，低成本测试心理特质对决策影响。
Interpolative Decoding: Exploring the Spectrum of Personality Traits in LLMs
- 用对立提示对加插值参数，实现人格维度的平滑控制。
- 在经济博弈中复现人类心理研究结果，验证行为模仿有效性。
- 可尝试匹配真人玩家行为，适合心理学与人机交互研究者。
近期研究探索将大语言模型（LLMs）作为人类代理，用于模拟、调查和行为研究。尽管LLMs不具备人类心理，但其能以足够高的保真度模拟人类行为，展现比传统规则代理更丰富的细节和多样性。一个关键研究方向是人格对决策的影响，但为每个性格特征设计提示带来实验开销并降低可复现性。为此，我们采用插值解码：将人格的每个维度表示为一对对立提示，并通过插值参数在该维度上模拟行为变化。实验表明，插值解码能可靠调节大五人格各维度得分。进一步验证显示，该方法使LLMs在经济博弈中复现人类心理研究中的决策模式。最后，我们初步尝试通过系统搜索插值空间中的点，实现对特定人类玩家行为的“数字孪生”——即让模型复现其在协作游戏中的实际行动。
原文摘要 · Abstract (English)
Recent research has explored using very large language models (LLMs) as proxies for humans in tasks such as simulation, surveys, and studies. While LLMs do not possess a human psychology, they often can emulate human behaviors with sufficiently high fidelity to drive simulations to test human behavioral hypotheses, exhibiting more nuance and range than the rule-based agents often employed in behavioral economics. One key area of interest is the effect of personality on decision making, but the requirement that a prompt must be created for every tested personality profile introduces experimental overhead and degrades replicability. To address this issue, we leverage interpolative decoding, representing each dimension of personality as a pair of opposed prompts and employing an interpolation parameter to simulate behavior along the dimension. We show that interpolative decoding reliably modulates scores along each of the Big Five dimensions. We then show how interpolative decoding causes LLMs to mimic human decision-making behavior in economic games, replicating results from human psychological research. Finally, we present preliminary results of our efforts to ``twin'' individual human players in a collaborative game through systematic search for points in interpolation space that cause the system to replicate actions taken by the human subject.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。