LLM 能否捕捉人类偏好？
Can LLMs Capture Human Preferences?
AI总结：
本文评估 GPT-3.5/GPT-4 模拟人类跨期偏好的能力，发现其耐心低于人类且受语言影响，并提出 chain-of-thought conjoint 结合主题建模以辅助假设生成。
摘要：
我们探讨了大型语言模型（LLM），尤其是 OpenAI 的 GPT-3.5 和 GPT-4，在模拟人类调查受访者并引出偏好方面的可行性，重点关注跨期选择。借助关于跨期贴现的大量文献作为基准，我们考察了 LLM 在多种语言中的回答，并将其与人类回答进行比较，探究较早获得的较小奖励与较晚获得的较大奖励之间的偏好。研究结果表明，两个 GPT 模型都表现出比人类更低的耐心；其中 GPT-3.5 对较早奖励表现出词典式偏好，这与人类决策者不同。尽管 GPT-4 没有表现出词典式偏好，但其测得的贴现率仍显著高于人类。有趣的是，GPT 模型在弱将来时指代的语言（如德语和普通话）中表现出更高的耐心，这与认为语言结构和跨期偏好之间存在相关性的既有文献相一致。我们展示了如何提示 GPT 解释其决策——我们将这一过程称为“chain-of-thought conjoint（思维链联合分析）”——可以缓解但不能消除 LLM 与人类回答之间的差异。虽然直接使用 LLM 引出偏好可能产生误导性结果，但将 chain-of-thought conjoint 与主题建模相结合有助于生成假设，使研究人员能够探究偏好的基础。chain-of-thought conjoint 为营销人员提供了一个结构化框架，可利用 LLM 识别能够解释不同客户和情境间偏好异质性的潜在属性或因素。
英文摘要：
We explore the viability of Large Language Models (LLMs), specifically OpenAI's GPT-3.5 and GPT-4, in emulating human survey respondents and eliciting preferences, with a focus on intertemporal choices. Leveraging the extensive literature on intertemporal discounting for benchmarking, we examine responses from LLMs across various languages and compare them to human responses, exploring preferences between smaller, sooner, and larger, later rewards. Our findings reveal that both GPT models demonstrate less patience than humans, with GPT-3.5 exhibiting a lexicographic preference for earlier rewards, unlike human decision-makers. Though GPT-4 does not display lexicographic preferences, its measured discount rates are still considerably larger than those found in humans. Interestingly, GPT models show greater patience in languages with weak future tense references, such as German and Mandarin, aligning with existing literature that suggests a correlation between language structure and intertemporal preferences. We demonstrate how prompting GPT to explain its decisions, a procedure we term "chain-of-thought conjoint," can mitigate, but does not eliminate, discrepancies between LLM and human responses. While directly eliciting preferences using LLMs may yield misleading results, combining chain-of-thought conjoint with topic modeling aids in hypothesis generation, enabling researchers to explore the underpinnings of preferences. Chain-of-thought conjoint provides a structured framework for marketers to use LLMs to identify potential attributes or factors that can explain preference heterogeneity across different customers and contexts.
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。
