Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911921426399232 |
|---|---|
| author | Zhang, Yuzhe Zhang, Yipeng Gan, Yidong Yao, Lina Wang, Chen |
| author_facet | Zhang, Yuzhe Zhang, Yipeng Gan, Yidong Yao, Lina Wang, Chen |
| contents | Causal graph recovery is traditionally done using statistical estimation-based methods or based on individual's knowledge about variables of interests. They often suffer from data collection biases and limitations of individuals' knowledge. The advance of large language models (LLMs) provides opportunities to address these problems. We propose a novel method that leverages LLMs to deduce causal relationships in general causal graph recovery tasks. This method leverages knowledge compressed in LLMs and knowledge LLMs extracted from scientific publication database as well as experiment data about factors of interest to achieve this goal. Our method gives a prompting strategy to extract associational relationships among those factors and a mechanism to perform causality verification for these associations. Comparing to other LLM-based methods that directly instruct LLMs to do the highly complex causal reasoning, our method shows clear advantage on causal graph quality on benchmark datasets. More importantly, as causality among some factors may change as new research results emerge, our method show sensitivity to new evidence in the literature and can provide useful information for updating causal graphs accordingly. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_15301 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Models Zhang, Yuzhe Zhang, Yipeng Gan, Yidong Yao, Lina Wang, Chen Computation and Language Machine Learning Methodology Causal graph recovery is traditionally done using statistical estimation-based methods or based on individual's knowledge about variables of interests. They often suffer from data collection biases and limitations of individuals' knowledge. The advance of large language models (LLMs) provides opportunities to address these problems. We propose a novel method that leverages LLMs to deduce causal relationships in general causal graph recovery tasks. This method leverages knowledge compressed in LLMs and knowledge LLMs extracted from scientific publication database as well as experiment data about factors of interest to achieve this goal. Our method gives a prompting strategy to extract associational relationships among those factors and a mechanism to perform causality verification for these associations. Comparing to other LLM-based methods that directly instruct LLMs to do the highly complex causal reasoning, our method shows clear advantage on causal graph quality on benchmark datasets. More importantly, as causality among some factors may change as new research results emerge, our method show sensitivity to new evidence in the literature and can provide useful information for updating causal graphs accordingly. |
| title | Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Models |
| topic | Computation and Language Machine Learning Methodology |
| url | https://arxiv.org/abs/2402.15301 |