Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning
This work addresses the challenge of modeling human-like rule inference in AI, though it is incremental as it builds on existing LLM and probabilistic reasoning techniques.
The paper tackled the problem of inferring natural language rules through experiments by integrating Large Language Models with Monte Carlo algorithms for probabilistic inference, resulting in higher accuracy in recovering true rules and better experiment design compared to existing methods.
We give a model of how to infer natural language rules by doing experiments. The model integrates Large Language Models (LLMs) with Monte Carlo algorithms for probabilistic inference, interleaving online belief updates with experiment design under information-theoretic criteria. We conduct a human-model comparison on a Zendo-style task, finding that a critical ingredient for modeling the human data is to assume that humans also consider fuzzy, probabilistic rules, in addition to assuming that humans perform approximately-Bayesian belief updates. We also compare with recent algorithms for using LLMs to generate and revise hypotheses, finding that our online inference method yields higher accuracy at recovering the true underlying rule, and provides better support for designing optimal experiments.