Automating psychological hypothesis generation with AI: when large language models meet causal graph

Understand

Leveraging the synergy between causal knowledge graphs and a large language model (LLM), our study introduces a groundbreaking approach for computational hypothesis generation in psychology.

• We analyzed 43,312 psychology articles using a LLM to extract causal relation pairs.
• This analysis produced a specialized causal graph for psychology.
• Applying link prediction algorithms, we generated 130 potential psychological hypotheses focusing on `well-being', then compared them against research ideas conceived by doctoral scholars and those produced solely by the LLM.