跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2608.02877 · v2

Graph-of-Thoughts for LLM Causal Discovery with a Fairness-Pathway Case Study

首次提交 2026-08-04 04:59
版本更新 2026-11-18 14:22
雷达观测 2026-11-19 19:08
arXiv ↗PDF ↗

摘要

Methods that use large language models (LLMs) for causal discovery reason locally, deciding one variable pair or one node at a time, so they never compare alternative whole graphs. We introduce GoT-CD, a Graph-of-Thoughts method that asks an LLM for several complete candidate graphs from variable metadata alone, ranks them with a deterministic validity score, merges them under a hard union constraint, refines the merge, and projects the result to a DAG. We evaluate on Asia, Child, and an Alzheimer's disease graph with 100 samples and GPT-4o-mini. Over five seeds on Alzheimer's and Child, GoT-CD gives the highest mean F1 score and the lowest mean structural Hamming distance of the LLM methods, with 95% intervals of the difference excluding zero in seven of eight comparisons, and it returns a DAG in every run while using three LLM requests per graph. Replaying the logged runs without individual components attributes most of the gain to generating and merging several complete candidates. A case study on the effect of Sex on MOCA Score in the Alzheimer's graph shows the limits of structural scores: the fairness verdict drawn from the discovered graph disagrees with the reference verdict in twelve of fifteen LLM runs, including all five GoT-CD runs, which mostly drop the edge out of Sex. Graphs meant for a specific downstream analysis should therefore also be checked on the pathways that analysis depends on.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-18 14:22 · 最新观测版本

Graph-of-Thoughts for LLM Causal Discovery with a Fairness-Pathway Case Study

Methods that use large language models (LLMs) for causal discovery reason locally, deciding one variable pair or one node at a time, so they never compare alternative whole graphs. We introduce GoT-CD, a Graph-of-Thoughts method that asks an LLM for several complete candidate graphs from variable metadata alone, ranks them with a deterministic validity score, merges them under a hard union constraint, refines the merge, and projects the result to a DAG. We evaluate on Asia, Child, and an Alzheimer's disease graph with 100 samples and GPT-4o-mini. Over five seeds on Alzheimer's and Child, GoT-CD gives the highest mean F1 score and the lowest mean structural Hamming distance of the LLM methods, with 95% intervals of the difference excluding zero in seven of eight comparisons, and it returns a DAG in every run while using three LLM requests per graph. Replaying the logged runs without individual components attributes most of the gain to generating and merging several complete candidates. A case study on the effect of Sex on MOCA Score in the Alzheimer's graph shows the limits of structural scores: the fairness verdict drawn from the discovered graph disagrees with the reference verdict in twelve of fifteen LLM runs, including all five GoT-CD runs, which mostly drop the edge out of Sex. Graphs meant for a specific downstream analysis should therefore also be checked on the pathways that analysis depends on.

查看此版本解读 →查看此版本原文 ↗