Pith. sign in

REVIEW 4 cited by

Counterfactual Causal Inference in Natural Language with Large Language Models

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 2410.06392 v1 pith:FA5AXN6E submitted 2024-10-08 cs.CL cs.LG

classification cs.CLcs.LG
keywords causalcounterfactualdatalanguageinferencegraphmethodnatural
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Causal structure discovery methods are commonly applied to structured data where the causal variables are known and where statistical testing can be used to assess the causal relationships. By contrast, recovering a causal structure from unstructured natural language data such as news articles contains numerous challenges due to the absence of known variables or counterfactual data to estimate the causal links. Large Language Models (LLMs) have shown promising results in this direction but also exhibit limitations. This work investigates LLM's abilities to build causal graphs from text documents and perform counterfactual causal inference. We propose an end-to-end causal structure discovery and causal inference method from natural language: we first use an LLM to extract the instantiated causal variables from text data and build a causal graph. We merge causal graphs from multiple data sources to represent the most exhaustive set of causes possible. We then conduct counterfactual inference on the estimated graph. The causal graph conditioning allows reduction of LLM biases and better represents the causal estimands. We use our method to show that the limitations of LLMs in counterfactual causal reasoning come from prediction errors and propose directions to mitigate them. We demonstrate the applicability of our method on real-world news articles.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data

    cs.CL 2026-07 conditional novelty 6.0 of 10

    DKCD uses retrieved domain-KG subgraphs to let LLMs discover latent factors and generate causal clues, yielding higher node F1 and lower extended SHD than COAT-style baselines on two synthetic medical datasets.

  2. Causal-Audit: Explicit and Auditable Graph-based Reasoning via Target-Aware Causal Chain Construction

    cs.AI 2026-04 conditional novelty 6.0 of 10

    A four-stage LLM framework that constructs, audits, and aggregates explicit causal chains outperforms prompting baselines on three context-free causal QA benchmarks.

  3. Causal Cartographer: From Mapping to Reasoning Over Counterfactual Worlds

    cs.AI 2025-05 reject novelty 6.0 of 10

    An LLM agent extracts a 975-variable causal graph from 2020 oil-price news and a second agent answers counterfactual queries by step-by-step causal reasoning.

  4. Simulating the Unseen: Crash Prediction Must Learn from What Did Not Happen

    cs.LG 2025-05 conditional novelty 4.0 of 10

    Crash prediction should learn from near-miss events and synthetic counterfactual scenarios, not just recorded crashes.

Pith tools