---
id: 20260901-T0-13
title: "LLM-Augmented Causal Discovery: Probabilistic Fusion of Edge Existence and Orientation"
url: https://ai.daily.yangsir.net/daily/20260901-T0-13
issue_date: 2026-09-01
publish_date: 2026-08-31T04:00:00.000Z
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2608.27472
---

# LLM-Augmented Causal Discovery: Probabilistic Fusion of Edge Existence and Orientation

arXiv:2608.27472v1 Announce Type: new Abstract: Bayesian network structure learning (BNSL) from observational data struggles with orientation identifiability, while large language models (LLMs) offer broad but often unreliable causal knowledge. We propose combining these complementary sources throug

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2608.27472)

**详情页**：https://ai.daily.yangsir.net/daily/20260901-T0-13

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*