about me
I am an applied ML + NLP researcher interested in explainability of LLMs used in natural language understanding tasks such as machine reading comprehension and information extraction – I want to understand the alignment between LLMs and humans in these problems.
I am currently a research fellow at the University of Michigan Medical School where I work on information extraction models on clinical text and their generalization abilities + models for early dementia prediction.
I came to Michigan from the Department of Computer Science, UCPH, CopeNLU group where I worked on the explainability of DNN models used in multi-hop reasoning systems, such as question answering, fact checking and natural language inference.
Before that, I worked as an NLP/ML engineer at Interactions. I developed DNN models for large scale entity extraction and linking, dialog systems, and sentiment classification. I also contributed to a DNN library that was used as the ML backend for the company.
During my Ph.D. from Penn State I worked in the CiteSeerX group on information extraction from scholarly figures and tables, information retrieval and crawling.
The best way to reach me is by 𝕏 @sagnikrayc.
News
- Dec 2023: EMNLP travel + talk.
- Nov 2023: PLOS ONE paper on gender bias in LLMs
- Oct 2023: Two papers accepted: 1. ConLL paper on Edge probing and 2. EMNLP main on interaction explanations.