Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Models
- URL: http://arxiv.org/abs/2402.15301v2
- Date: Tue, 18 Jun 2024 05:51:50 GMT
- Title: Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Models
- Authors: Yuzhe Zhang, Yipeng Zhang, Yidong Gan, Lina Yao, Chen Wang,
- Abstract summary: Causal graph recovery is traditionally done using statistical estimation-based methods or based on individual's knowledge about variables of interests.
We propose a novel method that leverages large language models (LLMs) to deduce causal relationships in general causal graph recovery tasks.
- Score: 23.438388321411693
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: 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.
Related papers
- ALCM: Autonomous LLM-Augmented Causal Discovery Framework [2.1470800327528843]
We introduce a new framework, named Autonomous LLM-Augmented Causal Discovery Framework (ALCM), to synergize data-driven causal discovery algorithms and Large Language Models.
The ALCM consists of three integral components: causal structure learning, causal wrapper, and LLM-driven causal refiner.
We evaluate the ALCM framework by implementing two demonstrations on seven well-known datasets.
arXiv Detail & Related papers (2024-05-02T21:27:45Z) - ExaRanker-Open: Synthetic Explanation for IR using Open-Source LLMs [60.81649785463651]
We introduce ExaRanker-Open, where we adapt and explore the use of open-source language models to generate explanations.
Our findings reveal that incorporating explanations consistently enhances neural rankers, with benefits escalating as the LLM size increases.
arXiv Detail & Related papers (2024-02-09T11:23:14Z) - Discovery of the Hidden World with Large Language Models [100.38157787218044]
We introduce COAT: Causal representatiOn AssistanT.
COAT incorporates LLMs as a factor proposer that extracts the potential causal factors from unstructured data.
LLMs can also be instructed to provide additional information used to collect data values.
arXiv Detail & Related papers (2024-02-06T12:18:54Z) - Multi-modal Causal Structure Learning and Root Cause Analysis [67.67578590390907]
We propose Mulan, a unified multi-modal causal structure learning method for root cause localization.
We leverage a log-tailored language model to facilitate log representation learning, converting log sequences into time-series data.
We also introduce a novel key performance indicator-aware attention mechanism for assessing modality reliability and co-learning a final causal graph.
arXiv Detail & Related papers (2024-02-04T05:50:38Z) - Zero-shot Causal Graph Extrapolation from Text via LLMs [50.596179963913045]
We evaluate the ability of large language models (LLMs) to infer causal relations from natural language.
LLMs show competitive performance in a benchmark of pairwise relations without needing (explicit) training samples.
We extend our approach to extrapolating causal graphs through iterated pairwise queries.
arXiv Detail & Related papers (2023-12-22T13:14:38Z) - Mitigating Large Language Model Hallucinations via Autonomous Knowledge
Graph-based Retrofitting [51.7049140329611]
This paper proposes Knowledge Graph-based Retrofitting (KGR) to mitigate factual hallucination during the reasoning process.
Experiments show that KGR can significantly improve the performance of LLMs on factual QA benchmarks.
arXiv Detail & Related papers (2023-11-22T11:08:38Z) - Can We Utilize Pre-trained Language Models within Causal Discovery
Algorithms? [0.2303687191203919]
Causal reasoning of Pre-trained Language Models (PLMs) relies solely on text-based descriptions.
We propose a new framework that integrates prior knowledge obtained from PLM with a causal discovery algorithm.
arXiv Detail & Related papers (2023-11-19T03:31:30Z) - Causal Inference Using LLM-Guided Discovery [34.040996887499425]
We show that the topological order over graph variables (causal order) alone suffices for causal effect inference.
We propose a robust technique of obtaining causal order from Large Language Models (LLMs)
Our approach significantly improves causal ordering accuracy as compared to discovery algorithms.
arXiv Detail & Related papers (2023-10-23T17:23:56Z) - From Query Tools to Causal Architects: Harnessing Large Language Models
for Advanced Causal Discovery from Data [19.264745484010106]
Large Language Models (LLMs) exhibit exceptional abilities for causal analysis between concepts in numerous societally impactful domains.
Recent research on LLM performance in various causal discovery and inference tasks has given rise to a new ladder in the classical three-stage framework of causality.
We propose a novel framework that combines knowledge-based LLM causal analysis with data-driven causal structure learning.
arXiv Detail & Related papers (2023-06-29T12:48:00Z) - Can Large Language Models Infer Causation from Correlation? [104.96351414570239]
We test the pure causal inference skills of large language models (LLMs)
We formulate a novel task Corr2Cause, which takes a set of correlational statements and determines the causal relationship between the variables.
We show that these models achieve almost close to random performance on the task.
arXiv Detail & Related papers (2023-06-09T12:09:15Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.