Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914991353888768 |
|---|---|
| author | Piriyakulkij, Wasu Top Langenfeld, Cassidy Le, Tuan Anh Ellis, Kevin |
| author_facet | Piriyakulkij, Wasu Top Langenfeld, Cassidy Le, Tuan Anh Ellis, Kevin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_06025 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning Piriyakulkij, Wasu Top Langenfeld, Cassidy Le, Tuan Anh Ellis, Kevin Artificial Intelligence Computation and Language 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. |
| title | Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2402.06025 |