arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.20252cs.CLcs.AIcs.LG
收藏

使用大语言模型建模目标人群的信念与偏好

Using LLMs to Model the Beliefs and Preferences of Targeted Populations

Toyota Research Institute(丰田研究所)

Keiichi Namikoshi, Alex Filipowicz, David A. Shamma, Rumen Iliev, Candice L. Hogan, Nikos Arechiga

AI总结:

本文研究如何微调大语言模型以建模特定人群的偏好,在电池电动汽车偏好调查上评估两种微调方法匹配群体统计和个体回答的能力,并分析温度参数对权衡的影响,同时提出新损失项以改进数值型回答的建模性能。

摘要:

我们考虑将大语言模型(LLM)对齐以建模人类群体偏好的问题。对特定人群的信念、偏好和行为进行建模可用于多种不同应用,例如针对新产品开展模拟焦点小组、进行虚拟调查以及测试行为干预措施,尤其是那些成本高昂、不切实际或不道德的干预措施。现有工作在利用LLM准确建模不同情境下人类行为方面取得的成功参差不齐。我们对两种知名的微调方法进行了基准测试和评估,并评估所得人群在电池电动汽车(BEVs)偏好调查中匹配真实人类受访者偏好的能力。我们评估模型在匹配群体整体统计数据方面的能力,以及在匹配个体回答方面的能力,并研究温度在控制这两者之间权衡中的作用。此外,我们提出并评估了一种新的损失项,以提高模型在需要数值回答的问题上的表现。

英文摘要:

We consider the problem of aligning a large language model (LLM) to model the preferences of a human population. Modeling the beliefs, preferences, and behaviors of a specific population can be useful for a variety of different applications, such as conducting simulated focus groups for new products, conducting virtual surveys, and testing behavioral interventions, especially for interventions that are expensive, impractical, or unethical. Existing work has had mixed success using LLMs to accurately model human behavior in different contexts. We benchmark and evaluate two well-known fine-tuning approaches and evaluate the resulting populations on their ability to match the preferences of real human respondents on a survey of preferences for battery electric vehicles (BEVs). We evaluate our models against their ability to match population-wide statistics as well as their ability to match individual responses, and we investigate the role of temperature in controlling the trade-offs between these two. Additionally, we propose and evaluate a novel loss term to improve model performance on responses that require a numeric response.

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。

↑