#  Rohit Bhattacharya (Williams College) 

 



####  calendar\_today Date and Time 

 **November 5, 2025** 

 12:00PM - 01:30PM EST 

####  pin\_drop Location 

 **CGIS Knafel Building, Room K354**  



 

 [ Join via Zoom arrow\_circle\_right ](https://harvard.zoom.us/j/93110218231?pwd=Gmka2cTdUty8AcWec90hWmcSllXtkP.1) 

 



 

### Title

Opportunities for Principled Use of AI for Causal Inference

### Abstract

Modern causal inference theory has advanced significantly in handling challenges that underlie observational data. Most of this theory, however, assumes clean, structured data, whereas real-world data sources like electronic health records contain a mix of both structured measurements and unstructured information (e.g., clinical notes.) In this context, state-of-the-art machine learning methods—particularly generative AI models trained on unstructured data—offer new opportunities for causal inference. While these tools are trained purely on associational tasks, I argue for some principled approaches to incorporating them into causal pipelines. Time permitting, I will present two concrete examples of this. The first concerns settings where information about unobserved confounding is captured in unstructured text data. The proposed method uses zero-shot models (e.g., large language models) to infer proxies from multiple instances of pre-treatment text and plugs them into the so-called proximal g-formula. I also briefly describe falsification heuristics and opportunities for sensitivity analysis for this method. The second example concerns settings involving high-dimensional treatments in the context of computational genomics. In this context, I describe how AlphaFold can be used as a form of interpretable dimension reduction for complex interventional queries involving mutations in protein sequences.



 

 



 

 

 Share on:- [     Facebook ](#)
- [     Twitter ](#)
- [     Linkedin ](#)
 


 Save: [ Add to calendar calendar\_today ](https://appliedstatsworkshopgov3009.hsites.harvard.edu/node/1337071/event-feed.ics)  Copy link link