Debrup Das

Photo of Debrup Das
Debrup Das
CS PhD Student
UMass Amherst

I am a 3rd year Computer Science PhD student at the Manning College of Information & Computer Sciences, University of Massachusetts Amherst, and a member of the Center for Intelligent Information Retrieval (CIIR). I am advised by Prof. Negin Rahimi. My broad research interests are in Information Retrieval (IR) and Natural Language Processing (NLP). Prior to this, I received a Dual Degree (Bachelors + Masters) in Mathematics and Computing from IIT Kharagpur, India, where I worked on tool-augmentation for mathematical reasoning in LLMs, supervised by Prof. Somak Aditya.

My research focuses on building retrievers that reason about relevance rather than matching surface similarity. I am currently working on: (1) scaling test-time thinking for reasoning-intensive retrieval, (2) reinforcement learning approaches to train retrievers optimized under embedding objectives and retrieval rewards, and (3) memory-augmented systems that retrieve and continually learn from past experiences.

News

Publications

Latent Personal Memory overview
Latent Personal Memory: Represent Personal Memory as Dynamic Soft Prompts
Debrup Das, Avinash Amballa, Yashas Malur Saidutta, Vijay Srinivasan, Vivek Kulkarni, Srinivas Chappidi
EMNLP 2026 Findings
RaDeR overview
RaDeR: Reasoning-aware Dense Retrieval Models
Debrup Das, Sam O'Nuallain, Negin Rahimi
EMNLP 2025 Main
SMAB overview
SMAB: MAB based Word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation
Saurabh Kumar Pandey, Sachin Vashistha, Debrup Das, Somak Aditya, Monojit Choudhury
NAACL 2025 Main
MathSensei overview
MathSensei: A Tool-Augmented Large Language Model for Mathematical Reasoning
Debrup Das, Debopriyo Banerjee, Somak Aditya, Ashish Kulkarni
NAACL 2024 Main