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
Zero-shot Causal Graph Extrapolation from Text via LLMs
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.
Forward citations
Cited by 3 Pith papers
-
ORCA: An End-to-End Interactive Copilot for Optimized Root Cause Analysis
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.
-
Implicit Causal Graph Construction in Text via Chain Discovery
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.
-
InsightFlow: LLM-Driven Synthesis of Patient Narratives for Mental Health into Causal Models
LLMs generate 5P causal graphs from 46 psychotherapy intake transcripts that match human expert graphs in structure and meaning, with moderate clinical usefulness ratings.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.