On 100 list-function tasks, LLM hypothesis search approaches human-level acquisition (0.487 vs 0.521 mean test accuracy) and clearly beats direct program generation (0.359), with hypothesis generation as the main error source.
Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction
On 100 list-function tasks, LLM hypothesis search approaches human-level acquisition (0.487 vs 0.521 mean test accuracy) and clearly beats direct program generation (0.359), with hypothesis generation as the main error source.