Large Language Models are Effective Priors for Causal Graph Discovery

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Darvariu, Victor-Alexandru, Hailes, Stephen, Musolesi, Mirco
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913359498051584
author Darvariu, Victor-Alexandru
Hailes, Stephen
Musolesi, Mirco
author_facet Darvariu, Victor-Alexandru
Hailes, Stephen
Musolesi, Mirco
contents Causal structure discovery from observations can be improved by integrating background knowledge provided by an expert to reduce the hypothesis space. Recently, Large Language Models (LLMs) have begun to be considered as sources of prior information given the low cost of querying them relative to a human expert. In this work, firstly, we propose a set of metrics for assessing LLM judgments for causal graph discovery independently of the downstream algorithm. Secondly, we systematically study a set of prompting designs that allows the model to specify priors about the structure of the causal graph. Finally, we present a general methodology for the integration of LLM priors in graph discovery algorithms, finding that they help improve performance on common-sense benchmarks and especially when used for assessing edge directionality. Our work highlights the potential as well as the shortcomings of the use of LLMs in this problem space.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13551
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Large Language Models are Effective Priors for Causal Graph Discovery
Darvariu, Victor-Alexandru
Hailes, Stephen
Musolesi, Mirco
Machine Learning
Artificial Intelligence
Causal structure discovery from observations can be improved by integrating background knowledge provided by an expert to reduce the hypothesis space. Recently, Large Language Models (LLMs) have begun to be considered as sources of prior information given the low cost of querying them relative to a human expert. In this work, firstly, we propose a set of metrics for assessing LLM judgments for causal graph discovery independently of the downstream algorithm. Secondly, we systematically study a set of prompting designs that allows the model to specify priors about the structure of the causal graph. Finally, we present a general methodology for the integration of LLM priors in graph discovery algorithms, finding that they help improve performance on common-sense benchmarks and especially when used for assessing edge directionality. Our work highlights the potential as well as the shortcomings of the use of LLMs in this problem space.
title Large Language Models are Effective Priors for Causal Graph Discovery
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2405.13551