Debjit Paul
Hi there! I’m a Research Scientist at Noah’s Ark Lab, London.
Previously, I was 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 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
| 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. |
| Jan 23, 2025 | Excited to share that our paper, INCLUDE, has been accepted at ICLR 2025! |
| Jan 23, 2025 | One paper is accepted at NAACL 2025 (FIPO: Fallacy-Informed Preference Optimization) |
