Email /
Twitter / Google Scholar / Semantic Scholar
I am a Senior Research Engineer at Meta Reality Labs working in the Smart Glasses Language AI team. My current research interests revolve around the training and alignment of large language models (LLMs) for downstream generative tasks like Question Answering. Before this, I was working as an Applied Scientist II at Amazon Alexa AI on LLMs and Question Answering systems. Prior to this, I graduated from the University of Wisconsin-Madison with a Masters in Computer Science in May 2020. I completed my Masters Thesis under the guidance of Prof. Yingyu Liang on representation learning paradigms and their application to text classification. Prior to this, I completed my Bachelors in Computer Science and Engineering from IIT Bombay in August 2018 where I was advised by Prof. Sunita Sarawagi.
News and Updates
| Jun 2024: | Our paper on measuring retrieval complexity in open domain question answering systems got accepted to the Findings of ACL 2024. |
| Mar 2024: | Our paper on multi-source attribution for long form LLM-generated responses got accepted at NAACL 2024. |
| Jan 2024: | Our paper on LLM-based proactive suggested QA for information seeking intent resolution got accepted to the Findings of EACL 2024 |
| Oct 2023: | I am serving as an Area Chair in the Question Answering track for EACL 2024 (ARR Action Editor) |
| Oct 2023: | I joined Meta as a Senior Research Engineer working in the Smart Glasses Language AI team |
| Sep 2023: | Our paper on automatic QA evaluation of LLM-generated answers got accepted at IJCNLP-AACL 2023 as an oral presentation |
| Jun 2023: | I am serving as an Area Chair in the Question Answering track for EMNLP 2023 |
| May 2023: | Our paper on LLM-based answer generation using feedback from automatic QA evaluators got accepted at ACL 2023 |
| May 2023: | Our paper on pre-training transformers for contextual answer selection got accepted at ACL 2023 |
| Dec 2022: | I attended EMNLP 2022 in Abu Dhabi, UAE to present two papers on pre-training and answer generation |
| Oct 2022: | Our paper on knowledge transfer from answer ranking to answer generation models got accepted at EMNLP 2022 |
| Oct 2022: | Our paper on pre-training transformers by exploiting document structure for answer selection got accepted at EMNLP 2022 |
| Jul 2022: | Our paper on analysis of attentive walk-aggregating GNNs got accepted to Transactions on Machine Learning Research (TMLR) journal |
| Jul 2022: | I attended NAACL 2022 in Seattle, WA to present our paper on multi-sentence inference |
| May 2022: | I attended ACL 2022 in Dublin, Ireland |
| May 2022: | Pre-print on pre-training transformers by exploiting paragragph and document structure for answer sentence selection released |
| Apr 2022: | Our paper "Paragraph-based Transformer Pretraining for Multi-Sentence Inference" got accepted at NAACL 2022 |
| Nov 2021: | Pre-print on analysis of attentive walk-aggregating GNNs released |
| Aug 2021: | Our paper "Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering" got accepted at EMNLP 2021 as an oral presentation |
| Aug 2021: | Our paper "Towards Robustness to Label Noise in Text Classification via Noise Modeling" got accepted at CIKM 2021 |
| Jul 2021: | I was recognised for being in the Top 10% of the reviewers for ICML 2021 |
| Jul 2021: | I was recognised for being an Outstanding Reviewer for ACL 2021 |
| Apr 2021: | Paper on text classification with noisy labels accepted at two ICLR 2021 Workshops: RobustML and S2D-OLAD |
| Jan 2021: | Pre-print on text classification with noisy labels released |
| Dec 2020: | I was recognised for being an Outstanding Reviewer for EMNLP 2020 |
| Oct 2020: | I was recognised for being in the Top 10% of the reviewers for NeurIPS 2020 |
| Sep 2020: | Our paper "Functional Regularization for Representation Learning: A Unified Theoretical Perspective" got accepted to NeurIPS 2020 |
| Sep 2020: | Our paper "BAE: BERT-based Adversarial Examples for Text Classification" got accepted at EMNLP 2020 in the main conference |
| Sep 2020: | Our paper "Beyond Fine-tuning: Few-Sample Sentence Embedding Transfer" got accepted at AACL 2020 |
| Jul 2020: | Our paper "Can Adversarial Weight Perturbations Inject Neural Backdoors?" got accepted at CIKM 2020 |
| Jun 2020: | I joined Amazon Alexa AI Search as an Applied Scientist |
| May 2020: | Survey on advances in Quantum Deep Learning released |
| May 2020: | Defended my Master's Thesis on representation learning paradigms and their application to text classification |
| Apr 2020: | Pre-print on fine-tuning BERT for data scarce text classification released |
| Apr 2020: | Pre-print on generating adversarial examples for NLP using BERT released |
| Feb 2020: | Presented our paper on transformers for answer selection at AAAI 2020, New York City |
| Nov 2019: | Paper on transformers for answer selection accepted for oral presentation at AAAI 2020 |
| Oct 2019: | Paper on making inference graphs interpretable for face recognition accepted at IVCNZ 2019, New Zealand |
| Sep 2019: | Paper on stochastic bandits with delayed composite feedback accepted at NeurIPS 2019 Workshop on ML with Guarantees |
| Jun 2019: | Two posters accepted at the Midwest Machine Learning Symposium(MMLS) 2019 |
| May 2019: | I joined Amazon Alexa Search at Manhattan Beach, CA as an Applied Scientist Intern under Alessandro Moschitti |
| Nov 2018: | My co-author Shiv Shankar presented our paper at EMNLP 2018, Brussels, Belgium |
| Sep 2018: | I joined the Department of Computer Science at the University of Wisconsin-Madison as a Masters student |
| Aug 2018: | Short paper on differentiable hard attention for seq2seq learning accepted at EMNLP 2018 |
| May 2018: | Defended my Bachelor's Thesis on structured attention models for seq2seq learning |