Aman Sinha

About Me

I am a final year PhD student at Université de Lorraine, Nancy, France, under the supervision of Marianne Clausel, Mathieu Constant and Xavier Coubez. My research involves exploring the behavior of text data and language models and their interaction, focusing on the intersection of the medical domain and Natural Language Processing. Recently, I’ve been interested in the interaction between model performance, data perception variability, and interpretability.

And more recently, I’ve developed a fondness for hallucinations in large language models.
Here are some outcomes: Mu-SHROOM 🍄, SHROOM-CAP 🦙👒 and CHOMPS

Research Interests

• Medical Language Understanding
• Natural Language Processing

News

• [Sept. 2025] SLAN got accepted at TS4H NeurIPS 2025.
• [Sept. 2025] Got one abstract accepted at ESMO AI Congress 2025.
• [July 2025] Presenting a poster at ICML 2025 on "Simplicity is not as simple as you think" [Poster]
• [July 2025] Attended ELLIS Summer School: AI for Health @ EPFL, Laussane, Switzerland.
• [June 2025] Presenting a poster at SMM4H 2025 on "Limitations of PLMs in MLU tasks" [Poster]
• [June 2025] Got one paper accepted at Workshop on Actionable Interpretability @ ICML 2025.
• [June 2025] Gave a talk at JdS 2025 on "Data complexity is not Data uncertainty" [Slides]
• [May 2025] CHOMPS 2025 got accepted at AACL-IJCNLP 2025, Mumbai, India. Stay tuned!
• [May 2025] Got one paper accepted at ACL 2025, Vienna, Austria.
• [Feb. 2025] Will be organizing MLP-LLM Workshop @ CORIA-TALN 2025, Marseille, France.
• [Oct. 2024] Joined the PC team for the UncertaiNLP Workshop @ EMNLP 2025, Suzhou, China.
• [Jul. 2024] Joined the organizing team for Mu-SHROOM at SemEval 2025 @ ACL 2025, Vienna, Austria.

Relevant Publications

[Complete list: Google Scholar]