Bio

Hi, I am Niyar R Barman, an M2 student at Université de Toulouse, working with Dr. Nicholas Asher.

I work on reasoning in language models and mechanistic interpretability. I have papers at EMNLP 2023 (outstanding paper) and SIGDIAL 2025.

My research asks when models are actually reasoning and when they are just using patterns that look right on benchmarks but fail under distribution shift. I build structured reasoning setups, run mechanistic experiments to find and measure shortcut behavior inside networks, and design compute strategies that keep representations rich while cutting overhead. I test these ideas with causal interventions on model internals, out of distribution evaluations, and targeted ablations.

Currently writing CUDA/Triton kernels to learn what happens at the hardware level (the log).

Open to research and industry roles starting October 2026.

You can reach me at: niyar-r.barman[at]utoulouse[.]fr

News

  • Sept 2025: Started M.S. in Interactions of Computer Science and Mathematics for AI at Université de Toulouse, France
  • 2025: DIMSUM: Discourse in Mathematical Reasoning as a Supervision Module accepted at SIGDIAL 2025
  • Jan 2025: Returned to IRIT, Toulouse for a second full-time research internship
  • May 2024: Started first full-time research internship at IRIT, Toulouse, France
  • Dec 2023: Counter Turing Test CT² presented at EMNLP 2023, received Outstanding Paper Award
  • Jan 2023: Started remote research internship at the Artificial Intelligence Institute, University of South Carolina, USA
  • Dec 2021: Started B.Tech. in Electronics and Communication Engineering at National Institute of Technology Silchar, India

Publications

selected · all
SIGDIAL 2025
DIMSUM: Discourse in Mathematical Reasoning as a Supervision Module
Niyar R Barman, Krish Sharma, Nicholas Asher, Akshay Chaturvedi
Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue
This work explores how discourse structures can be used as supervision for improving mathematical reasoning in large language models.
paper
EMNLP 2023
● outstanding paper award
Counter Turing Test CT²: AI-Generated Text Detection is Not as Easy as You May Think
Megha Chakraborty, S. M. Towhidul Islam Tonmoy, S. M. Mehedi Zaman, Krish Sharma, Niyar R Barman, Chandan Gupta, Shreya Gautam, Tanay Kumar, Vinija Jain, Aman Chadha, Amit P. Sheth, Amitava Das
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Introduces the AI Detectability Index and challenges current approaches to AI-generated text detection.
paper
arXiv 2024
The Brittleness of Image Watermarking Techniques: Investigating Visual Paraphrasing for De-Watermarking AI-Generated Images
Niyar R Barman, Krish Sharma, Ashhar Aziz, Shashwat Bajpai, Shwetangshu Biswas, Aman Chadha, Vasu Sharma, Amitava Das
paper
IEEE CICT 2023
A Transformer-Based Approach to Automate Disease Prediction from Patient Descriptions
Niyar R Barman, Krish Sharma, Ranjay Hazra
paper
FIRE 2023
Addressing Hate Speech: ATLANTIS for Efficient Hate Span Detection
Niyar R Barman, Krish Sharma, Yashraj Poddar, Adwaitha Vatupal, Partha Pakray
paper

Education

  • 2025 - 2026, M2 Master Interactions de l’Informatique et des Mathématiques pour l’IA, Université de Toulouse, France
  • 2021 - 2025, Bachelors of Technology in Electronics and Communication Engineering, National Institute of Technology Silchar, India

Research Experience

  • May 2024 - Jul 2024, Jan 2025 - Mar 2025, Research Intern, Institut de Recherche en Informatique de Toulouse, France
  • Jan 2023 - Dec 2024, Research Intern, Artificial Intelligence Institute of University of South Carolina, United States