大型語言模型與具有心靈理論的代理人有多遠？

How FaR Are Large Language Models From Agents with Theory-of-Mind?

October 4, 2023

作者: Pei Zhou, Aman Madaan, Srividya Pranavi Potharaju, Aditya Gupta, Kevin R. McKee, Ari Holtzman, Jay Pujara, Xiang Ren, Swaroop Mishra, Aida Nematzadeh, Shyam Upadhyay, Manaal Faruqui

cs.AI

摘要

「思考是為了行動。」人類可以從觀察中推斷他人的心智狀態，這種能力被稱為心智理論（ToM），並隨後根據這些推斷實際行動。現有的問答基準，如ToMi，要求模型回答有關故事中角色信仰的問題，但並不測試模型是否能利用這些推斷來引導其行動。我們提出了一種新的大型語言模型（LLMs）評估範式：思考為了行動（T4D），要求模型將對他人心智狀態的推斷與社交場景中的行動相連接。對T4D的實驗表明，像GPT-4和PaLM 2這樣的LLMs似乎擅長追蹤故事中角色的信念，但它們在將這種能力轉化為策略行動方面遇到困難。我們的分析顯示，LLMs面臨的核心挑戰在於識別有關心智狀態的隱含推斷，而不是像ToMi那樣明確問及，這些推斷導致在T4D中選擇正確的行動。為了彌合這一差距，我們引入了一個零-shot提示框架，名為預見和反思（FaR），該框架提供一種鼓勵LLMs預測未來挑戰並思考潛在行動的推理結構。FaR將GPT-4在T4D上的表現從50%提升至71%，優於其他提示方法，如思維鏈和自問自答。此外，FaR可以泛化應用於多樣的分布之外的故事結構和場景，這些場景也需要ToM推斷來選擇行動，一貫優於其他方法，包括少量上下文學習。

English

"Thinking is for Doing." Humans can infer other people's mental states from observations--an ability called Theory-of-Mind (ToM)--and subsequently act pragmatically on those inferences. Existing question answering benchmarks such as ToMi ask models questions to make inferences about beliefs of characters in a story, but do not test whether models can then use these inferences to guide their actions. We propose a new evaluation paradigm for large language models (LLMs): Thinking for Doing (T4D), which requires models to connect inferences about others' mental states to actions in social scenarios. Experiments on T4D demonstrate that LLMs such as GPT-4 and PaLM 2 seemingly excel at tracking characters' beliefs in stories, but they struggle to translate this capability into strategic action. Our analysis reveals the core challenge for LLMs lies in identifying the implicit inferences about mental states without being explicitly asked about as in ToMi, that lead to choosing the correct action in T4D. To bridge this gap, we introduce a zero-shot prompting framework, Foresee and Reflect (FaR), which provides a reasoning structure that encourages LLMs to anticipate future challenges and reason about potential actions. FaR boosts GPT-4's performance from 50% to 71% on T4D, outperforming other prompting methods such as Chain-of-Thought and Self-Ask. Moreover, FaR generalizes to diverse out-of-distribution story structures and scenarios that also require ToM inferences to choose an action, consistently outperforming other methods including few-shot in-context learning.