Hi! I'm a predoctoral researcher in the Department of Empirical Inference at the Max Planck Institute for Intelligent Systems in Tübingen, working with Bernhard Schölkopf and Zhijing Jin. I also do research at the Jinesis Lab at the University of Toronto.

I'm interested in CAUSALITY and LLMs. I want to understand how LLMs acquire reasoning capabilities, and I think causality provides a great framework to study this. I also lead the Causal AI Scientist project, building LLM agents that run causal analyses on real-world data.

Before this, I did my MSc in Informatics at TU Munich and my BSc in Computer Science at Jacobs University Bremen, both in Germany 🇩🇪. I grew up in Kathmandu, Nepal 🇳🇵.

Outside research, I play football ⚽, go to the gym 🏋️, play guitar 🎸, cook a lot (hand-pulled noodles are my weakness 🍜), travel whenever I can ✈️, and love well-written blog posts about lives very different from mine. 📖 Reach out if you want to chat! :)

 

CV / email / github / linkedin / twitter / google scholar

Rahul B. Shrestha at the Golden Gate Bridge
 

Selected Works

CauSciBench: Can LLMs Automate Causal Inference in Real-World Scientific Research?

CauSciBench: Can LLMs Automate Causal Inference in Real-World Scientific Research?

Sawal Acharya*, Terry Jingchen Zhang*, Andrew Kim†, Rahul B. Shrestha†, et al.
International Conference on Machine Learning (ICML), 2026
[paper] [code]
Causal AI Scientist: Towards End-to-End Causal Inference with Large Language Models

Causal AI Scientist: Towards End-to-End Causal Inference with Large Language Models

Sawal Acharya, Rahul B. Shrestha, Jacob T. Emmerson, Vishal Verma, Devansh Bhardwaj, Samuel Simko, Punya Syon Pandey, Anahita Haghighat, Yongjin Yang, Dominik Janzing, Mrinmaya Sachan, Bernhard Schölkopf, Zhijing Jin
Under review, 2026
[paper] [code]
Causal Tutor: An Interactive Learning and Research Tool for Causal Inference

Causal Tutor: An Interactive Learning and Research Tool for Causal Inference

Zaryab Muhammad Akram*, Yara Allam*, Rahul B. Shrestha*, Omar El Herraoui, Aryan Amit Barsainyan, Kosei Uemura, Xianlin Sun, Terry Jingchen Zhang, Bernhard Schölkopf, Zhijing Jin
Under review, 2026
[paper] [code]
CLAIM-FUSE: Causal Discovery with Heterogenous and Uncertain Knowledge

CLAIM-FUSE: Causal Discovery with Heterogenous and Uncertain Knowledge

Yahang Qi, Erivan Inan, Rahul B. Shrestha, Luke Zhang, Dehan Kong, Zhijing Jin
Under review, 2026
[paper]
From Causal Parrots to Causal Prophets? Towards Sound Causal Reasoning with Large Language Models

From Causal Parrots to Causal Prophets? Towards Sound Causal Reasoning with Large Language Models

Rahul B. Shrestha*, Simon Malberg*, Georg Groh
International Conference on NLP for Digital Humanities (NLP4DH), 2025
[paper]

* denotes equal contribution, † denotes core contributor