Tanay Dixit

Hello!, I am an MSCS student at the University of Illinois, Urbana Champaign, where I am working with Prof. Jiawei Han. My research mainly focuses on LLMs and improving evaluation techniques. I am honoured to be a Siebel Scholar (Class of 2025) I graduated from the Indian Institute of Technology Madras in 2023 with a bachelor's degree in ECE. While at IIT Madras, I worked with Prof. Mitesh Khapra

I’m looking for Research Engineering/ Applied Scientists roles, please reach out if you think I would be a good fit.


Research & Experience
  • LLM Evaluations & Applications: Built an interactive tool for performing LLM prompt migrations efficiently [1]. Increased the usability and interpretability of LLM-based NL2SQL pipelines by introducing intermediate representations [2]
  • Interpretability & Trustworthiness: Developed a retrieval augmented counterfactual data generation techniques to improve model generalization [3] , and improved the factuality of summarization systems by training models using a ranking loss [4]
  • NLP Evaluation: Showed NLG metrics contain several evaluation blind spots and proposed a better framework to meta-evaluate metrics [6]. Released a large meta-evaluation dataset and metrics for low-resource translation evaluation [5]

Email  /  LinkedIn  /  Google Scholar  /  Semantic Scholar

Internships

University of Southern California
Summer 2022
ML Research Intern (NSF REU Scholar)

Faithful Summarization

University of Washington
Spring 2022
ML Research Intern

Model Interpretability

Microsoft Research
Summer 2023
ML Research Engineer

Natural language to SQL

Adobe
Summer 2024
ML Intern

Interactive Evaluation






Publications
RETAIN: Interactive Tool for Regression Testing Guided LLM Migration
Tanay Dixit, Daniel Lee, Sally Fang, Sai Sree Harsha, Anirudh Sureshan, Akash Maharaj, Yunyao Li
EMNLP 2024 Demo
[Paper]


PwR: Exploring the Role of Representations in Conversational Programming
Pradyumna YM, Vinod Ganesan, Dinesh Kumar Arumugam, Meghna Gupta, Nischith Shadagopan, Tanay Dixit, Sameer Segal, Pratyush Kumar, Mohit Jain, Sriram Rajamani

[Arxiv]


Improving Factuality of Abstractive Summarization without Sacrificing Summary Quality
Tanay Dixit, Fei Wang, Muhao Chen
ACL 2023
[Paper][Code]


IndicMT Eval: A Dataset to Meta-Evaluate Machine Translation Metrics for Indian Languages
Ananya Sai, Tanay Dixit, Vignesh Nagarajan, Anoop Kunchukuttan, Pratyush Kumar, Mitesh M. Khapra, Raj Dabre
ACL 2023
[Paper][Code]


CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation
Tanay Dixit,Bhargavi Paranjape, Hannaneh Hajishirzi, Luke Zettlemoyer
EMNLP 2022 (Findings)
[Paper][Code]


SUPER-NATURALINSTRUCTIONS: Generalization via Declarative Instructions on 1600+ NLP Tasks
Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, Anjana Arunkumar, Arjun Ashok, Arut Selvan Dhanasekaran, Atharva Naik, David Stap, Eshaan Pathak, Giannis Karamanolakis, Haizhi Gary Lai, Ishan Purohit, Ishani Mondal, Jacob Anderson, Kirby Kuznia, Krima Doshi, Maitreya Patel, Kuntal Kumar Pal, Mehrad Moradshahi, Mihir Parmar, Mirali Purohit, Neeraj Varshney, Phani Rohitha Kaza, Pulkit Verma, Ravsehaj Singh Puri, Rushang Karia, Shailaja Keyur Sampat, Savan Doshi, Siddhartha Mishra, Sujan Reddy, Sumanta Patro, Tanay Dixit, Xudong Shen, Chitta Baral, Yejin Choi, Noah A Smith, Hannaneh Hajishirzi, Daniel Khashabi
EMNLP, 2022
[Paper][Code]




Perturbation CheckLists for Evaluating NLG Evaluation Metrics
Ananya B Sai, Tanay Dixit, Dev Yashpal Sheth, Sreyas Mohan, Mitesh M Khapra
EMNLP, 2021
[Paper][Code]


NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation
Kaustubh D. Dhole, Varun Gangal, Sebastian Gehrmann, ... , Tanay Dixit, ... (many authors)
NEJLT 2023 (GEM Workshop, IJCNLP 2021)
[Paper][Code]




Template from here