Debjit Paul

Hi there! I’m a Senior Researcher at Microsoft Research India.

Previously, I was a Research Scientist at Huawei Noah’s Ark Lab, London, and a Postdoctoral Researcher at EPFL, working with Antoine Bosselut, Boi Faltings, and Robert West. Before EPFL, I completed my Ph.D. under the supervision of Anette Frank in the Department of Computational Linguistics at Heidelberg University, where I was also part of the Research Training Group AIPHES.

My work has been recognised with a SAC Highlight at ACL 2026 and an Outstanding Paper Award at NAACL 2025. I serve as an Area Chair for ACL and EMNLP conferences.

My overarching research objective is to enhance the reasoning capabilities of artificial agents by advancing their ability to understand the complex interplay between language, knowledge representation, and cognitive reasoning processes. To accomplish this goal, I have focused my investigations on three areas:

Neuro-Symbolic Reasoning. Understanding and reasoning about the world requires integrating structured knowledge with learned representations. My research develops computational models that combine symbolic knowledge graphs and logical structures with neural architectures, enabling AI systems to perform compositional reasoning while generalising robustly to novel situations. [1,2, 3, 4]

Trustworthy AI. As AI systems become more capable, ensuring their reliability becomes critical. My research addresses challenges such as hallucination, unfaithful reasoning, and misalignment with human values. I develop methods for generating faithful explanations, detecting and mitigating factual errors, and aligning model behaviour through human and AI feedback. [5,6,7]

Agentic AI. The next generation of AI systems will need to plan, reason, and act autonomously in complex environments. My research focuses on building agents that can decompose complex tasks, leverage external tools and knowledge sources, and engage in multi-step decision-making while maintaining coherent long-term goals. [8,9,10]

news

Jul 07, 2026	🏆 Our paper Parity-Aware Byte-Pair Encoding was selected as a SAC Highlight at https://2026.aclweb.org/ in San Diego.
Mar 30, 2026	🎉 Excited to share that I’ve joined Microsoft Research India as a Senior Researcher! Looking forward to pushing the boundaries of AI reasoning, knowledge representation, and cognitive reasoning in this new chapter.
Jan 26, 2026	Our paper, A Benchmark for Deep Information Synthesis, has been accepted to ICLR 2026.
Jan 03, 2026	Our paper, Process Evaluation for Agentic Systems, has been accepted to the Findings of EACL 2026.
May 04, 2025	Our paper FIPO: Fallacy-Informed Preference Optimisation received the Outstanding Paper Award 🏆 at NAACL 2025.

latest posts

Sep 30, 2025	What Children Know That AI Doesn't: Learning Through Experience, Not Text
Sep 28, 2025	Understanding FLOPs, MFU, and Computational Efficiency in LLM Training: From Dense Transformers to MoE Architectures
Jan 15, 2025	FIPO: Fallacy-Informed Preference Optimization - Steering LLMs Toward Logically Sound Arguments

selected publications

A Benchmark for Deep Information Synthesis

Debjit Paul, Daniel Murphy, Milan Gritta, Ronald Cardenas, Victor Prokhorov, Lena Sophia Bolliger, Aysim Toker, Roy Miles, Andreea-Maria Oncescu, Jasivan Alex Sivakumar, Philipp Borchert, Ismail Elezi, Meiru Zhang, Ka Yiu Lee, Guchun Zhang, Gerasimos Lampouras, and Jun Wang

In The Fourteenth International Conference on Learning Representations, Apr 2026

Bib PDF

@inproceedings{paul-etal-2026-deepinfosynth,
  title = {A Benchmark for Deep Information Synthesis},
  author = {Paul, Debjit and Murphy, Daniel and Gritta, Milan and Cardenas, Ronald and Prokhorov, Victor and Bolliger, Lena Sophia and Toker, Aysim and Miles, Roy and Oncescu, Andreea-Maria and Sivakumar, Jasivan Alex and Borchert, Philipp and Elezi, Ismail and Zhang, Meiru and Lee, Ka Yiu and Zhang, Guchun and Lampouras, Gerasimos and Wang, Jun},
  booktitle = {The Fourteenth International Conference on Learning Representations},
  month = apr,
  year = {2026},
}

ACL

Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization

Negar Foroutan, Clara Meister, Debjit Paul, Joel Niklaus, Sina Ahmadi, Antoine Bosselut, and Rico Sennrich

In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2026

SAC Highlight arXiv Bib

Selected as a SAC Highlight at ACL 2026 — the Area Chair’s Award, given by Senior Area Chairs to recognise one paper per track for originality, technical excellence, and potential impact on the field.

@inproceedings{foroutan-etal-2026-parity,
  title = {Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization},
  author = {Foroutan, Negar and Meister, Clara and Paul, Debjit and Niklaus, Joel and Ahmadi, Sina and Bosselut, Antoine and Sennrich, Rico},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for
      Computational Linguistics (Volume 1: Long Papers)},
  month = jul,
  year = {2026},
  address = {San Diego, California, United States},
  publisher = {Association for Computational Linguistics},
      Award, given by Senior Area Chairs to recognise one paper per
      track for originality, technical excellence, and potential
      impact on the field.},
}

A Logical Fallacy-Informed Framework for Argument Generation

Luca Mouchel, Debjit Paul, Shaobo Cui, Robert West, Antoine Bosselut, and Boi Faltings

In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Apr 2025

DOI Bib PDF Code

@inproceedings{mouchel-etal-2025-logical,
  title = {A Logical Fallacy-Informed Framework for Argument Generation},
  author = {Mouchel, Luca and Paul, Debjit and Cui, Shaobo and West, Robert and Bosselut, Antoine and Faltings, Boi},
  editor = {Chiruzzo, Luis and Ritter, Alan and Wang, Lu},
  booktitle = {Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)},
  month = apr,
  year = {2025},
  address = {Albuquerque, New Mexico},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2025.naacl-long.374/},
  doi = {10.18653/v1/2025.naacl-long.374},
  pages = {7296--7314},
  isbn = {979-8-89176-189-6},
}

Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning

Debjit Paul, Robert West, Antoine Bosselut, and Boi Faltings

In Findings of EMNLP: 2024, Nov 2024

Bib PDF Code

@inproceedings{paul2024reasoning,
  title = {Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning},
  author = {Paul, Debjit and West, Robert and Bosselut, Antoine and Faltings, Boi},
  month = nov,
  year = {2024},
  publisher = {Association for Computational Linguistics},
  booktitle = {Findings of EMNLP: 2024},
  url = {https://debjitpaul.github.io/reasoningmatter},
  journal = {arXiv preprint arXiv:2402.13950},
}

REFINER: Reasoning Feedback on Intermediate Representations

Debjit Paul, Mete Ismayilzada, Maxime Peyrard, Beatriz Borges, Antoine Bosselut, Robert West, and Boi Faltings

In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), Mar 2024

Bib PDF Code

@inproceedings{Paul2023REFINERRF,
  title = {REFINER: Reasoning Feedback on Intermediate Representations},
  author = {Paul, Debjit and Ismayilzada, Mete and Peyrard, Maxime and Borges, Beatriz and Bosselut, Antoine and West, Robert and Faltings, Boi},
  booktitle = {Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month = mar,
  year = {2024},
  url = {https://aclanthology.org/2024.eacl-long.67},
}