Hello, I am Somin!

I am a CS Ph.D. candidate in Khoury College of Computer Sciences at Northeastern University, advised by Byron Wallace and Silvio Amir.

I study how to extract and communicate insights from large text corpora by combining natural language processing and structured information extraction. My recent projects span clinical literature, and distillation techniques for large language models.

All publications (selected publications)

2025

• Who Taught You That? Tracing Teachers in Model Distillation. Somin Wadhwa, Chantal Shaib, Silvio Amir and Byron C. Wallace. Association for Computational Linguistics (ACL). Vienna, Austria. July 2025.

2024

• Investigating Mysteries of CoT-Augmented Distillation. Somin Wadhwa, Silvio Amir and Byron C. Wallace. Empirical Methods in Natural Language Processing (EMNLP). Miami, Florida, USA. November 2024.

• Learning from Natural Language Explanations for Generalizable Entity Matching. Somin Wadhwa, Adit Krishnan, Runhui Wang, Byron C. Wallace and Chris Kong. Empirical Methods in Natural Language Processing (EMNLP). Miami, Florida, USA. November 2024.

• Distilling Event Sequence Knowledge From Large Language Models. Somin Wadhwa, Oktie Hassanzadeh, Debarun Bhattacharjya, Ken Barker and Jian Ni. International Semantic Web Conference (ISWC). Baltimore, Maryland, USA. November 2024.

2023

• Jointly Extracting Interventions, Outcomes, and Findings from RCT Reports with LLMs. Somin Wadhwa, Jay DeYoung, Benjamin Nye and Byron C. Wallace. Machine Learning for Health Conference (MLHC). New York City, New York, USA. August 2023.

• Revisiting Relation Extraction in the era of Large Language Models. Somin Wadhwa, Silvio Amir and Byron C. Wallace. Association for Computational Linguistics (ACL). Toronto, Canada. July 2023.

2022

• RedHOT: A Corpus of Annotated Medical Questions, Experiences, and Claims on Social Media. Somin Wadhwa, Vivek Khetan, Silvio Amir and Byron C. Wallace. European Chapter of the Association for Computational Linguistics (EACL.) Dubrovnik, Croatia. May 2023.

2021

• Towards System-Initiative Conversational Information Seeking. Somin Wadhwa and Hamed Zamani. Design of Experimental Search & Information REtrieval Systems (DESIRES). Padua, Italy. September 2021.

2020

• CommunityClick: Capturing and Reporting Community Feedback from Town Halls to Improve Inclusivity. M Jasim, Pooya Khaloo, Somin Wadhwa, Amy X. Zhang, Ali Sarvghad and Narges Mahyar. ACM Conference on Computer Supported Cooperative Work (CSCW). Minnepolis, Minnesota, USA. October 2020. Best paper award . [bibtex] [video]

• CommunityClick: Towards Improving Inclusivity in Town Halls. M Jasim, Pooya Khaloo, Somin Wadhwa, Amy X. Zhang, Ali Sarvghad and Narges Mahyar. Companion Publication of the 2020 Conference on Computer Supported Cooperative Work and Social Computing (CSCW).

• Semi-Automating Knowledge Base Construction for Cancer Genetics. Somin Wadhwa, Kanhua Yin, M.D., Kevin S. Hughes, M.D. and Byron C. Wallace. Automated Knowledge Base Construction (AKBC). Irvine, California, USA. June 2020. [bibtex] [slides]

2019

• BitterSweet: Building machine learning models for predicting the bitter and sweet taste of small molecules. Rudraksh Tuwani, Somin Wadhwa and Ganesh Bagler. Scientific Reports, Nature. [ris]

2018

• A hierarchical anatomical classification schema for prediction of phenotypic side effects. Somin Wadhwa, Aishwarya Gupta, Shubham Dokania, Rakesh Kanji and Ganesh Bagler. PLOS One. [bibtex]