Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
72 tokens/sec
GPT-4o
61 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
8 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

The Mind in the Machine: A Survey of Incorporating Psychological Theories in LLMs (2505.00003v1)

Published 28 Mar 2025 in cs.CL

Abstract: Psychological insights have long shaped pivotal NLP breakthroughs, including the cognitive underpinnings of attention mechanisms, formative reinforcement learning, and Theory of Mind-inspired social modeling. As LLMs continue to grow in scale and complexity, 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, including data, pre-training, post-training, and evaluation&application. Our survey integrates insights from cognitive, developmental, behavioral, social, personality psychology, and psycholinguistics. Our analysis highlights 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 future NLP research.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (8)
  1. Zizhou Liu (5 papers)
  2. Ziwei Gong (10 papers)
  3. Lin Ai (15 papers)
  4. Zheng Hui (27 papers)
  5. Run Chen (10 papers)
  6. Colin Wayne Leach (2 papers)
  7. Michelle R. Greene (5 papers)
  8. Julia Hirschberg (37 papers)