# Can Large Language Models Help Experimental Design for Causal Discovery?

arXiv: https://arxiv.org/abs/2503.01139 · HTML: https://mlsanity.com/paper/2503.01139/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 3 Mar 2025.

## Builds on (most cited first, 25 of 25)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Differentiable Causal Discovery from Interventional Data](https://mlsanity.com/paper/2007.01754/) (2020)
- [D'ya like DAGs? A Survey on Structure Learning and Causal Discovery](https://mlsanity.com/paper/2103.02582/) (2021)
- [Causal Parrots: Large Language Models May Talk Causality But Are Not Causal](https://mlsanity.com/paper/2308.13067/) (2023)
- [Can Large Language Models Infer Causation from Correlation?](https://mlsanity.com/paper/2306.05836/) (2023)
- [Learning Neural Causal Models from Unknown Interventions](https://mlsanity.com/paper/1910.01075/) (2019)
- [The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4](https://mlsanity.com/paper/2311.07361/) (2023)
- [Efficient Neural Causal Discovery without Acyclicity Constraints](https://mlsanity.com/paper/2107.10483/) (2021)
- [Can large language models build causal graphs?](https://mlsanity.com/paper/2303.05279/) (2023)
- [Causal Discovery with Language Models as Imperfect Experts](https://mlsanity.com/paper/2307.02390/) (2023)
- [Do Large Language Models know what humans know?](https://mlsanity.com/paper/2209.01515/) (2022)
- [Understanding Causality with Large Language Models: Feasibility and Opportunities](https://mlsanity.com/paper/2304.05524/) (2023)
- [Efficient Causal Graph Discovery Using Large Language Models](https://mlsanity.com/paper/2402.01207/) (2024)
- [Interventions, Where and How? Experimental Design for Causal Models at Scale](https://mlsanity.com/paper/2203.02016/) (2022)
- [Learning Neural Causal Models with Active Interventions](https://mlsanity.com/paper/2109.02429/) (2021)
- [Passive learning of active causal strategies in agents and language models](https://mlsanity.com/paper/2305.16183/) (2023)
- [Unpacking Large Language Models with Conceptual Consistency](https://mlsanity.com/paper/2209.15093/) (2022)
- [Evaluating structure learning algorithms with a balanced scoring function](https://mlsanity.com/paper/1905.12666/) (2019)
- [Discovering and Reasoning of Causality in the Hidden World with Large Language Models](https://mlsanity.com/paper/2402.03941/) (2024)
- [Trust Your nabla: Gradient-based Intervention Targeting for Causal Discovery](https://mlsanity.com/paper/2211.13715/) (2022)
- [On the Three Demons in Causality in Finance: Time Resolution, Nonstationarity, and Latent Factors](https://mlsanity.com/paper/2401.05414/) (2023)

## Built on by (most cited first, 11 of 11)

- [From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery](https://mlsanity.com/paper/2505.13259/) (2025)
- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [A Survey of AI Scientists](https://mlsanity.com/paper/2510.23045/) (2025)
- [LLM Cannot Discover Causality, and Should Be Restricted to Non-Decisional Support in Causal Discovery](https://mlsanity.com/paper/2506.00844/) (2025)
- [CausalGame: Benchmarking Causal Thinking of LLM Agents in Games](https://mlsanity.com/paper/2607.04293/) (2026)
- [ARCHE: A Novel Task to Evaluate LLMs on Latent Reasoning Chain Extraction](https://mlsanity.com/paper/2511.12485/) (2025)
- [CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad](https://mlsanity.com/paper/2603.14575/) (2026)
- [Accepted with Minor Revisions: Value of AI-Assisted Scientific Writing](https://mlsanity.com/paper/2511.12529/) (2025)
- [Why LLMs Fail at Causal Discovery and How Interventional Agents Escape](https://mlsanity.com/paper/2605.27567/) (2026)
- [DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data](https://mlsanity.com/paper/2607.09348/) (2026)
- [ACED-Bench: Evaluating How LLM Agents Acquire and Act on Causal Evidence](https://mlsanity.com/paper/2610.14381/) (2026)

## Abstract (arXiv)

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.