基礎模型中的類人情感認知

Human-like Affective Cognition in Foundation Models

September 18, 2024

作者: Kanishk Gandhi, Zoe Lynch, Jan-Philipp Fränken, Kayla Patterson, Sharon Wambu, Tobias Gerstenberg, Desmond C. Ong, Noah D. Goodman

cs.AI

摘要

理解情感對於人類互動和體驗至關重要。 人類能夠輕易從情境或面部表情中推斷情感，從情感中推斷情境，並進行各種其他情感認知。現代人工智慧在這些推斷方面表現如何？我們引入了一個評估框架，用於測試基礎模型中的情感認知。從心理學理論出發，我們生成了1,280個多樣化情境，探索評估、情感、表情和結果之間的關係。我們在精心選擇的條件下評估了基礎模型（GPT-4、Claude-3、Gemini-1.5-Pro）和人類（N = 567）的能力。我們的結果顯示，基礎模型往往與人類直覺一致，匹配或超過參與者間的一致性。在某些情況下，模型表現“超人”——它們比平均人類更能預測主觀人類判斷。所有模型都受益於思維鏈推理。這表明基礎模型已經獲得了對情感及其對信念和行為的影響的人類化理解。

English

Understanding emotions is fundamental to human interaction and experience. Humans easily infer emotions from situations or facial expressions, situations from emotions, and do a variety of other affective cognition. How adept is modern AI at these inferences? We introduce an evaluation framework for testing affective cognition in foundation models. Starting from psychological theory, we generate 1,280 diverse scenarios exploring relationships between appraisals, emotions, expressions, and outcomes. We evaluate the abilities of foundation models (GPT-4, Claude-3, Gemini-1.5-Pro) and humans (N = 567) across carefully selected conditions. Our results show foundation models tend to agree with human intuitions, matching or exceeding interparticipant agreement. In some conditions, models are ``superhuman'' -- they better predict modal human judgements than the average human. All models benefit from chain-of-thought reasoning. This suggests foundation models have acquired a human-like understanding of emotions and their influence on beliefs and behavior.