Shashank Gupta

I'm a researcher on the Aristo team at the Allen Institute for AI (AI2) in Seattle.

Broadly, I am interested in building general-purpose AI agents that can:
(1) reason about complex problems through natural language rationalization,
(2) faithfully express their uncertainty in their knowledge and reasoning, and
(3) continuously improve through self-reflection and human feedback.

My current research focus is on AI for Scientific Discovery. I am particularly interested in AI for Math (e.g., Automated Theorem Proving, better foundation models for Math), building agents for finding supporting/contrary evidence from literature, and retrieval-augmented and memory architectures for supporting these use cases.

CV | E-Mail | Google Scholar | Semantic Scholar | Github | Twitter

profile photo
Selected Projects
sym

[NEW] SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories
Ben Bogin, Kejuan Yang, Shashank Gupta, Kyle Richardson, Erin Bransom, Peter Clark, Ashish Sabharwal, Tushar Khot

EMNLP 2024
🏆 Outstanding Paper Award 🏆
paper | code | dataset

sym

[NEW] AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents
Harsh Trivedi, Tushar Khot, Mareike Hartmann, [...], Shashank Gupta, Ashish Sabharwal, Niranjan Balasubramanian

ACL 2024
🏆 Best Resource Paper Award 🏆
paper | website | code | video | poster | X (Twitter)

sym

LLM-SR: Scientific Equation Discovery via Programming with Large Language Models
Parshin Shojaee, Kazem Meidani, Shashank Gupta, Amir Barati Farimani, Chandan K Reddy

Preprint (2024)
paper | code

sym

Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
Shashank Gupta, Vaishnavi Shrivastava, Ameet Deshpande, Ashwin Kalyan, Peter Clark, Ashish Sabharwal, Tushar Khot

ICLR 2024
paper | website | code | poster | data | X (Twitter)

sym

Self-Refine: Iterative Refinement with Self-Feedback
Aman Madaan, Niket Tandon, [...], Shashank Gupta, [...], Peter Clark

NeurIPS 2023
paper | website | code | poster | Forbes

sym

Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners
Shashank Gupta, Subhabrata Mukherjee, Krishan Subudhi, Eduardo Gonzalez, Damien Jose, Ahmed H. Awadallah, Jianfeng Gao

Microsoft AI Journal, 2022
paper

sym

Knowledge Infused Decoding

Ruibo Liu, Guoqing Zheng, Shashank Gupta, Radhika Gaonkar, Chongyang Gao, Soroush Vosoughi, Milad Shokouhi, Ahmed Hassan Awadallah

ICLR 2022
paper | code

sym

Exploring Low-Cost Transformer Model Compression for Large-Scale Commercial Reply Suggestions
Vaishnavi Shrivastava*, Radhika Gaonkar*, Shashank Gupta*, Abhishek Jha

*equal contribution
Microsoft AI Journal, 2021
paper | blog post

sym

CogCompNLP: Your Swiss Army Knife for NLP
Daniel Khashabi, Mark Sammons, [...], Shashank Gupta, [...], Dan Roth

LREC 2018
paper | code

sym

Web-scale entity annotation using MapReduce
Shashank Gupta, Varun Chandramouli, Soumen Chakrabarti

HiPC 2013
paper | slides


Template credits: Unnat, and Jon