AINeutralarXiv – CS AI · 5h ago5/10
🧠
Human Adults and LLMs as Scientists: Who Benefits from Active Exploration?
Research comparing human adults and large language models on causal learning tasks reveals that active exploration significantly improves humans' ability to identify conjunctive causal rules (where multiple causes must occur simultaneously), though conjunctive reasoning remains harder than disjunctive reasoning. State-of-the-art LLMs approach human performance on accuracy but demonstrate less efficient exploration strategies and similar reasoning gaps.