About

I am Soumadeep /ˌʃoʊ.moʊˈðiːp/ (pronounced Show-mo-deep), a Postdoctoral Researcher at ANITI, University of Toulouse.

I earned my PhD in Computer Science from the Indian Statistical Institute, Kolkata, where I was advised by Prof. Utpal Garain.

My doctoral research focused on integrating key symbolic AI principles—such as domain constraint awareness and logical coherence—into deep learning systems. Currently, I am exploring techniques to better understand and enhance reasoning in Large Language Models (LLMs), with a focus on constraint adherence, alignment, and reliability.

Recent Works

• The Synergistic Integration of Access Control Management and Large Language Model Agents: A Survey

  Francesco Periti and Soumadeep Saha
  TechRxiv | 2026

• KisMATH: Do LLMs Have Knowledge of Implicit Structures in Mathematical Reasoning?

  Soumadeep Saha, A. Chaturvedi, S. Saha, U. Garain, N. Asher
  Accepted to TACL (In press) | 2025