Large Language Models for Zero-shot Inference of Causal Structures in Biology Article Swipe

MAKE IMPACT

Richard Moulange , Nan Rosemary Ke , Sach Mukherjee · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2503.04347

Genes, proteins and other biological entities influence one another via causal molecular networks. Causal relationships in such networks are mediated by complex and diverse mechanisms, through latent variables, and are often specific to cellular context. It remains challenging to characterise such networks in practice. Here, we present a novel framework to evaluate large language models (LLMs) for zero-shot inference of causal relationships in biology. In particular, we systematically evaluate causal claims obtained from an LLM using real-world interventional data. This is done over one hundred variables and thousands of causal hypotheses. Furthermore, we consider several prompting and retrieval-augmentation strategies, including large, and potentially conflicting, collections of scientific articles. Our results show that with tailored augmentation and prompting, even relatively small LLMs can capture meaningful aspects of causal structure in biological systems. This supports the notion that LLMs could act as orchestration tools in biological discovery, by helping to distil current knowledge in ways amenable to downstream analysis. Our approach to assessing LLMs with respect to experimental data is relevant for a broad range of problems at the intersection of causal learning, LLMs and scientific discovery.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2503.04347

PDF

https://arxiv.org/pdf/2503.04347

OA Status

green

OpenAlex ID

https://openalex.org/W4416113187

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4416113187

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2503.04347

Digital Object Identifier

Title

Large Language Models for Zero-shot Inference of Causal Structures in Biology

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-03-06

Full publication date if available

Authors

Richard Moulange, Nan Rosemary Ke, Sach Mukherjee

List of authors in order

Landing page

https://arxiv.org/abs/2503.04347

Publisher landing page

PDF URL

https://arxiv.org/pdf/2503.04347

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2503.04347

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload