Can Large Language Models Help Experimental Design for Causal Discovery?

• URL: http://arxiv.org/abs/2503.01139v2
• Date: Tue, 04 Mar 2025 04:19:03 GMT
• Title: Can Large Language Models Help Experimental Design for Causal Discovery?
• Authors: Junyi Li, Yongqiang Chen, Chenxi Liu, Qianyi Cai, Tongliang Liu, Bo Han, Kun Zhang, Hui Xiong,
• Abstract summary: Large Language Model Guided Intervention Targeting (LeGIT) is a robust framework that effectively incorporates LLMs to augment existing numerical approaches for the intervention targeting in causal discovery.<n>LeGIT demonstrates significant improvements and robustness over existing methods and even surpasses humans.
• Score: 94.66802142727883
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Designing proper experiments and selecting optimal intervention targets is a longstanding problem in scientific or causal discovery. Identifying the underlying causal structure from observational data alone is inherently difficult. Obtaining interventional data, on the other hand, is crucial to causal discovery, yet it is usually expensive and time-consuming to gather sufficient interventional data to facilitate causal discovery. Previous approaches commonly utilize uncertainty or gradient signals to determine the intervention targets. However, numerical-based approaches may yield suboptimal results due to the inaccurate estimation of the guiding signals at the beginning when with limited interventional data. In this work, we investigate a different approach, whether we can leverage Large Language Models (LLMs) to assist with the intervention targeting in causal discovery by making use of the rich world knowledge about the experimental design in LLMs. Specifically, we present Large Language Model Guided Intervention Targeting (LeGIT) -- a robust framework that effectively incorporates LLMs to augment existing numerical approaches for the intervention targeting in causal discovery. Across 4 realistic benchmark scales, LeGIT demonstrates significant improvements and robustness over existing methods and even surpasses humans, which demonstrates the usefulness of LLMs in assisting with experimental design for scientific discovery.

Related papers

• Regularized Multi-LLMs Collaboration for Enhanced Score-based Causal Discovery [13.654021365091305]
  We explore the potential of using large language models (LLMs) to enhance causal discovery approaches.<n>We propose a general framework to utilise the capacity of not only one but multiple LLMs to augment the discovery process.
  arXiv  Detail & Related papers  (2024-11-27T01:56:21Z)
• LLM-initialized Differentiable Causal Discovery [0.0]
  Differentiable causal discovery (DCD) methods are effective in uncovering causal relationships from observational data. However, these approaches often suffer from limited interpretability and face challenges in incorporating domain-specific prior knowledge. We propose Large Language Models (LLMs)-based causal discovery approaches that provide useful priors but struggle with formal causal reasoning.
  arXiv  Detail & Related papers  (2024-10-28T15:43:31Z)
• CAnDOIT: Causal Discovery with Observational and Interventional Data from Time-Series [4.008958683836471]
  CAnDOIT is a causal discovery method to reconstruct causal models using both observational and interventional data. The use of interventional data in the causal analysis is crucial for real-world applications, such as robotics. A Python implementation of CAnDOIT has also been developed and is publicly available on GitHub.
  arXiv  Detail & Related papers  (2024-10-03T13:57:08Z)
• Discovery of the Hidden World with Large Language Models [95.58823685009727]
  This paper presents Causal representatiOn AssistanT (COAT) that introduces large language models (LLMs) to bridge the gap. LLMs are trained on massive observations of the world and have demonstrated great capability in extracting key information from unstructured data. COAT also adopts CDs to find causal relations among the identified variables as well as to provide feedback to LLMs to iteratively refine the proposed factors.
  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)
• Trust Your $\nabla$: Gradient-based Intervention Targeting for Causal Discovery [49.084423861263524]
  In this work, we propose a novel Gradient-based Intervention Targeting method, abbreviated GIT. GIT 'trusts' the gradient estimator of a gradient-based causal discovery framework to provide signals for the intervention acquisition function. We provide extensive experiments in simulated and real-world datasets and demonstrate that GIT performs on par with competitive baselines.
  arXiv  Detail & Related papers  (2022-11-24T17:04:45Z)
• Active Learning for Optimal Intervention Design in Causal Models [11.294389953686945]
  We develop a causal active learning strategy to identify interventions that are optimal, as measured by the discrepancy between the post-interventional mean of the distribution and a desired target mean. We apply our approach to both synthetic data and single-cell transcriptomic data from Perturb-CITE-seq experiments to identify optimal perturbations that induce a specific cell state transition.
  arXiv  Detail & Related papers  (2022-09-10T20:40:30Z)
• Interventions, Where and How? Experimental Design for Causal Models at Scale [47.63842422086614]
  Causal discovery from observational and interventional data is challenging due to limited data and non-identifiability. In this paper, we incorporate recent advances in Bayesian causal discovery into the Bayesian optimal experimental design framework. We demonstrate the performance of the proposed method on synthetic graphs for both linear and nonlinear SCMs as well as on the in-silico single-cell gene regulatory network dataset, DREAM.
  arXiv  Detail & Related papers  (2022-03-03T20:59:04Z)
• Learning Neural Causal Models with Active Interventions [83.44636110899742]
  We introduce an active intervention-targeting mechanism which enables a quick identification of the underlying causal structure of the data-generating process. Our method significantly reduces the required number of interactions compared with random intervention targeting. We demonstrate superior performance on multiple benchmarks from simulated to real-world data.
  arXiv  Detail & Related papers  (2021-09-06T13:10:37Z)

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.