Scholar
Sagnik Ray Choudhury
Google Scholar ID: xl5b_vcAAAAJ
University of North Texas
Citations & Impact
Citations
498
H-index
16
i10-index
19
Publications
20
Co-authors
12
list available
Publications
Resume (English only)
Academic Achievements
- 1. Two papers accepted to AACL IJCNLP. 2. Co-PC chair for the 2025 ACM/IEEE Joint Conference of Digital Libraries (JCDL’25). 3. Pre-print on measuring political bias in LLMs. 4. Paper on automated generation and extraction of limitations from scholarly text at EMNLP 2025. 5. Paper on predicting the scholarly impact of research papers using retrieval-augmented LLMs at SDP@ACL 2025. 6. Paper on generalization awarded prize at EMNLP 2024. 7. Paper on reproducibility accepted at CIKM 2024. 8. PLOS ONE paper on gender bias in LLMs. 9. Two papers accepted: one on edge probing at ConLL and another on interaction explanations at EMNLP main.
Research Experience
- 1. Previously an NLP Scientist at the National Board of Medical Examiners. 2. Worked at the University of Michigan Medical School on information extraction models on clinical text and their generalization abilities, as well as models for early dementia prediction. 3. Worked at the Department of Computer Science, UCPH, CopeNLU group, on the explainability of DNN models used in multi-hop reasoning systems, such as question answering, fact-checking, and natural language inference. 4. Post-Ph.D., worked as an NLP/ML engineer at Interactions, developing DNN models for large-scale entity extraction and linking, dialog systems, and sentiment classification, and contributed to a DNN library used as the ML backend for the company.
Education
- During his Ph.D. from Penn State, he worked in the CiteSeerX group on information extraction from scholarly figures and tables, information retrieval, and crawling.
Background
- Applied NLP/ML researcher. Asst prof @UNT. Research interests: 1. Explaining the behavior and limitations of LLMs, focusing on model bias and reasoning abilities; 2. Scholarly information processing to enhance users' experience with digital libraries.
Miscellany
- The best way to reach him is by email: sagnikrayc at gmail dot com. Not on any social media (X/bluesky/Insta/FB). LinkedIn profile not maintained.
