LLM-based Agents for Automated Confounder Discovery and Subgroup Analysis in Causal Inference
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909731039215616 |
|---|---|
| author | Lee, Po-Han Lin, Yu-Cheng Ku, Chan-Tung Hsu, Chan Huang, Pei-Cing Wu, Ping-Hsun Kang, Yihuang |
| author_facet | Lee, Po-Han Lin, Yu-Cheng Ku, Chan-Tung Hsu, Chan Huang, Pei-Cing Wu, Ping-Hsun Kang, Yihuang |
| contents | Estimating individualized treatment effects from observational data presents a persistent challenge due to unmeasured confounding and structural bias. Causal Machine Learning (causal ML) methods, such as causal trees and doubly robust estimators, provide tools for estimating conditional average treatment effects. These methods have limited effectiveness in complex real-world environments due to the presence of latent confounders or those described in unstructured formats. Moreover, reliance on domain experts for confounder identification and rule interpretation introduces high annotation cost and scalability concerns. In this work, we proposed Large Language Model-based agents for automated confounder discovery and subgroup analysis that integrate agents into the causal ML pipeline to simulate domain expertise. Our framework systematically performs subgroup identification and confounding structure discovery by leveraging the reasoning capabilities of LLM-based agents, which reduces human dependency while preserving interpretability. Experiments on real-world medical datasets show that our proposed approach enhances treatment effect estimation robustness by narrowing confidence intervals and uncovering unrecognized confounding biases. Our findings suggest that LLM-based agents offer a promising path toward scalable, trustworthy, and semantically aware causal inference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_07221 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM-based Agents for Automated Confounder Discovery and Subgroup Analysis in Causal Inference Lee, Po-Han Lin, Yu-Cheng Ku, Chan-Tung Hsu, Chan Huang, Pei-Cing Wu, Ping-Hsun Kang, Yihuang Machine Learning Artificial Intelligence Multiagent Systems Applications Methodology Estimating individualized treatment effects from observational data presents a persistent challenge due to unmeasured confounding and structural bias. Causal Machine Learning (causal ML) methods, such as causal trees and doubly robust estimators, provide tools for estimating conditional average treatment effects. These methods have limited effectiveness in complex real-world environments due to the presence of latent confounders or those described in unstructured formats. Moreover, reliance on domain experts for confounder identification and rule interpretation introduces high annotation cost and scalability concerns. In this work, we proposed Large Language Model-based agents for automated confounder discovery and subgroup analysis that integrate agents into the causal ML pipeline to simulate domain expertise. Our framework systematically performs subgroup identification and confounding structure discovery by leveraging the reasoning capabilities of LLM-based agents, which reduces human dependency while preserving interpretability. Experiments on real-world medical datasets show that our proposed approach enhances treatment effect estimation robustness by narrowing confidence intervals and uncovering unrecognized confounding biases. Our findings suggest that LLM-based agents offer a promising path toward scalable, trustworthy, and semantically aware causal inference. |
| title | LLM-based Agents for Automated Confounder Discovery and Subgroup Analysis in Causal Inference |
| topic | Machine Learning Artificial Intelligence Multiagent Systems Applications Methodology |
| url | https://arxiv.org/abs/2508.07221 |