| 2026 | ACL | Learning Faster with Better Tokens: Parameter-Efficient Vocabulary Adaptation for Specialized Text Summarization. | Gunjan Balde, Soumyadeep Roy, Mainack Mondal, Niloy Ganguly |
| 2026 | LREC | LongTailQA: Benchmarking LLMs and RAG Models on Disambiguated Long-Tail Entities. | William Xion, Uwe Hadler, Tim Cofala, Maximilian Idahl, Soumyadeep Roy, Wolfgang Nejdl |
| 2025 | ACL | Evaluation of LLMs in Medical Text Summarization: The Role of Vocabulary Adaptation in High OOV Settings. | Gunjan Balde, Soumyadeep Roy, Mainack Mondal, Niloy Ganguly |
| 2025 | ECAI | "Where does it hurt?" - Dataset and Study on Physician Intent Trajectories in Doctor Patient Dialogues. | Tom Rhr, Soumyadeep Roy, Fares Al Mohamad, Jens-Michalis Papaioannou, Wolfgang Nejdl, Felix A. Gers, Alexander Lser |
| 2025 | WSDM | Building Trustworthy AI Models for Medicine: From Theory to Applications. | Soumyadeep Roy, Sowmya S. Sundaram, Dominik Wolff, Niloy Ganguly |
| 2025 | WSDM | A Systematic Evaluation of Single-Cell Foundation Models on Cell-Type Classification Task. | Nicolas Steiner, Ziteng Li, Omid Vosoughi, Johanna Schrader, Soumyadeep Roy, Wolfgang Nejdl, Ming Tang |
| 2024 | ECAI | Unlocking Efficiency: Adaptive Masking for Gene Transformer Models. | Soumyadeep Roy, Shamik Sural, Niloy Ganguly |
| 2024 | EMNLP | Adaptive BPE Tokenization for Enhanced Vocabulary Adaptation in Finetuning Pretrained Language Models. | Gunjan Balde, Soumyadeep Roy, Mainack Mondal, Niloy Ganguly |
| 2024 | IJCAI | MEDVOC: Vocabulary Adaptation for Fine-tuning Pre-trained Language Models on Medical Text Summarization. | Gunjan Balde, Soumyadeep Roy, Mainack Mondal, Niloy Ganguly |
| 2024 | SIGIR | Beyond Accuracy: Investigating Error Types in GPT-4 Responses to USMLE Questions. | Soumyadeep Roy, Aparup Khatua, Fatemeh Ghoochani, Uwe Hadler, Wolfgang Nejdl, Niloy Ganguly |
| 2023 | ECAI | GENEMASK: Fast Pretraining of Gene Sequences to Enable Few-Shot Learning. | Soumyadeep Roy, Jonas Wallat, Sowmya S. Sundaram, Wolfgang Nejdl, Niloy Ganguly |
| 2021 | CIKM | Knowledge-Aware Neural Networks for Medical Forum Question Classification. | Soumyadeep Roy, Sudip Chakraborty, Aishik Mandal, Gunjan Balde, Prakhar Sharma, Anandhavelu Natarajan, Megha Khosla, Shamik Sural, Niloy Ganguly |