mlsanityData to 7 Oct 2026

Zero-shot Causal Graph Extrapolation from Text via LLMs

arXiv 2312.14670 ↗First posted 22 Dec 2023cs.AIcited by 15

Not on the map. Why?

Abstract (arXiv)

We evaluate the ability of large language models (LLMs) to infer causal relations from natural language. Compared to traditional natural language processing and deep learning techniques, LLMs show competitive performance in a benchmark of pairwise relations without needing (explicit) training samples. This motivates us to extend our approach to extrapolating causal graphs through iterated pairwise queries. We perform a preliminary analysis on a benchmark of biomedical abstracts with ground-truth causal graphs validated by experts. The results are promising and support the adoption of LLMs for such a crucial step in causal inference, especially in medical domains, where the amount of scientific text to analyse might be huge, and the causal statements are often implicit.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 9 of its 15 references that are in the map. First posted on arXiv 22 Dec 2023.

Builds on

9 of 15 references.

References · 9

  1. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  2. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 599
  3. 2017Deep Learning for Medical Image Analysiscited by 399
  4. 2023Can Large Language Models Infer Causation from Correlation?cited by 142
  5. 2017Comparative Study of CNN and RNN for Natural Language Processingcited by 81
  6. 2020A Survey on Text Classification: From Shallow to Deep Learningcited by 80
  7. 2023Large Language Models and Knowledge Graphs: Opportunities and Challengescited by 71
  8. 2023Understanding Causality with Large Language Models: Feasibility and Opportunitiescited by 53
  9. 2023Approximating Counterfactual Bounds while Fusing Observational, Biased and Randomised Data Sourcescited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 4; 2026: 7.

15 papers.

Sort:

By area:

  1. 2024ALCM: Autonomous LLM-Augmented Causal Discovery Frameworkcited by 29
  2. 2024Large Language Models and Causal Inference in Collaboration: A Surveycited by 26
  3. 2024Causality for Large Language Modelscited by 24
  4. 2024End-To-End Causal Effect Estimation from Unstructured Natural Language Datacited by 18
  5. 2025Causally Reliable Concept Bottleneck Modelscited by 17
  6. 2025Structure-Augmented Reasoning Generationcited by 2
  7. 2025Score-informed Neural Operator for Enhancing Ordering-based Causal Discoverycited by 2
  8. 2025StructSynth: Dependency Graphs as Generation Plans for Low-Data Tabular Synthesis with Language Modelscited by 0
  9. 2026Designing Computational Tools for Exploring Causal Relationships in Qualitative Datacited by 0
  10. 2026iTAG: Inverse Design for Natural Text Generation with Accurate Causal Graph Annotationscited by 0
  11. 2026InsightFlow: LLM-Driven Synthesis of Patient Narratives for Mental Health into Causal Modelscited by 0
  12. 2026ORCA: An End-to-End Interactive Copilot for Optimized Root Cause Analysiscited by 0
3 more
  1. 2026Implicit Causal Graph Construction in Text via Chain Discoverycited by 0
  2. 2026CausalSteward: An Agentic Divide-Conquer-Combine Copilot for Causal Discoverycited by 0
  3. 2026DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Datacited by 0