REVIEW 5 cited by
Large Language Models and Causal Inference in Collaboration: A Survey
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
Large Language Models and Causal Inference in Collaboration: A Survey
read the original abstract
Causal inference has shown potential in enhancing the predictive accuracy, fairness, robustness, and explainability of Natural Language Processing (NLP) models by capturing causal relationships among variables. The emergence of generative Large Language Models (LLMs) has significantly impacted various NLP domains, particularly through their advanced reasoning capabilities. This survey focuses on evaluating and improving LLMs from a causal view in the following areas: understanding and improving the LLMs' reasoning capacity, addressing fairness and safety issues in LLMs, complementing LLMs with explanations, and handling multimodality. Meanwhile, LLMs' strong reasoning capacities can in turn contribute to the field of causal inference by aiding causal relationship discovery and causal effect estimations. This review explores the interplay between causal inference frameworks and LLMs from both perspectives, emphasizing their collective potential to further the development of more advanced and equitable artificial intelligence systems.
Forward citations
Cited by 5 Pith papers
-
Generative Synthetic Data for Causal Inference: Pitfalls, Remedies, and Opportunities
Fully generative synthetic data preserves predictive utility but distorts ATE estimates due to a structural mismatch with prediction loss; a hybrid framework separating covariate generation from causal mechanisms impr...
-
CounterBench: Evaluating and Improving Counterfactual Reasoning in Large Language Models
Introduces CounterBench benchmark and CoIn iterative reasoning method showing LLMs perform near random on formal counterfactual tasks but improve substantially with guided backtracking.
-
Generative Synthetic Data for Causal Inference: Pitfalls, Remedies, and Opportunities
Fully generative synthetic tabular data distorts causal estimands like ATE despite good predictive fidelity, while a hybrid framework separating covariate generation from nuisance models substantially improves ATE pre...
-
Generative Synthetic Data for Causal Inference: Pitfalls, Remedies, and Opportunities
Prediction-tuned synthetic data can pass realism tests while distorting average treatment effects, and separating covariate generation from treatment/outcome modeling largely fixes it.
-
Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations
LLM explanations split into local and mechanistic tracks; the paper argues they are trustworthy only if they pass causal and contrastive stress tests, adapt to the explainee, and satisfy eight trust principles.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.