用心理学理论提升大模型的人类认知能力
A Review of Incorporating Psychological Theories in LLMs
- 从认知到社会心理，六大学派理论融入大模型研发
- 揭示当前心理机制应用中的研究空白与矛盾点
- 适合关注模型可解释性与人机交互的研究者
心理洞察长期推动自然语言处理的关键突破，从注意力机制到强化学习和社交建模。随着大语言模型（LLMs）的发展，学界逐渐认同心理学对模拟人类认知、行为与互动至关重要。本文系统回顾了心理学理论在大模型各发展阶段的应用路径，整合认知、发展、行为、社会、人格心理学及心理语言学六个子领域。通过分阶段分析，揭示当前心理理论融合的主流趋势与研究缺口。通过考察跨领域关联与内在张力，旨在弥合学科鸿沟，推动心理学更深入地融入自然语言处理研究。
原文摘要 · Abstract (English)
Psychological insights have long shaped pivotal NLP breakthroughs, from attention mechanisms to reinforcement learning and social modeling. As Large Language Models (LLMs) develop, there is a rising consensus that psychology is essential for capturing human-like cognition, behavior, and interaction. This paper reviews how psychological theories can inform and enhance stages of LLM development. Our review integrates insights from six subfields of psychology, including cognitive, developmental, behavioral, social, personality psychology, and psycholinguistics. With stage-wise analysis, we highlight current trends and gaps in how psychological theories are applied. By examining both cross-domain connections and points of tension, we aim to bridge disciplinary divides and promote more thoughtful integration of psychology into NLP research.
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。