Pith. sign in

REVIEW 3 cited by

Zero-shot Causal Graph Extrapolation from Text via LLMs

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.14670 v1 pith:ERRPQ2DF submitted 2023-12-22 cs.AI

Zero-shot Causal Graph Extrapolation from Text via LLMs

classification cs.AI
keywords causalllmslanguagebenchmarkgraphsnaturalpairwiserelations
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. ORCA: An End-to-End Interactive Copilot for Optimized Root Cause Analysis

    cs.AI 2026-05 unverdicted novelty 6.0

    ORCA is an agent-orchestrated interactive copilot that automates and guides end-to-end causal analysis from workflow selection to report generation across real-world use cases.

  2. Implicit Causal Graph Construction in Text via Chain Discovery

    cs.CL 2026-04 conditional novelty 6.0

    LLMs can construct implicit causal graphs between text-extracted cause-effect pairs via chain discovery, validated against a curated database of 1,560 scientifically validated causal pairs from IPCC reports.

  3. InsightFlow: LLM-Driven Synthesis of Patient Narratives for Mental Health into Causal Models

    cs.CL 2026-04 unverdicted novelty 5.0

    LLMs generate 5P causal graphs from 46 psychotherapy intake transcripts that match human expert graphs in structure and meaning, with moderate clinical usefulness ratings.