CV

Education

• Master of Science - Digital Engineering, Otto von Guericke Universität, Magdeburg, Germany, 2022
• Bachelor of Technology - Electronics and Communication Engineering, Sree Chitra Thirunal College of Engineering, Trivandrum, India, 2016

Work experience

• 07/2022 - Present: Research Associate / PhD Student, Bielefeld University, Bielefeled, Germany
  • LLM4KMU
• 05/2022 - 07/2025: Research Engineer, Fraunhofer IAIS, Dresden, Germany
  • Developed text embedding models from decoder-only LLMs using contrastive learning. Resultant models significantly outperformed the base models and were replaced as retriever models in the In-House Conversational QA system.
  • Conducted research on the applicability of LLMs to address classification and regression tasks with tabular data from ERP systems.
  • Built Conversational QA systems exploring conventional and advanced RAG approaches. Fine-tuned and evaluated both retriever and reader models. Extended the system by incorporating model-agnostic explanations to help users understand the model responses better.
  • Explored modular and end-to-end approaches for task-oriented dialog systems, focusing on LLMs as customer service agents. Conducted comprehensive evaluation of open-source LLMs fine tuned with different PEFT techniques.
• 04/2021 - 12/2021: Master Thesis, AUDI AG, Ingolstadt, Germany
  • Developed “BiTe-REx”, a bilingual text retrieval system (English - German) with model-agnostic explanations specifically designed for the automotive domain. This system facilitates competitor analysis tasks for users working in both English and German.
• 08/2019 - 04/2021: Student Research Assistant, ifak - Institut für Automation und Kommunikation, Magdeburg, Germany
  • Developed “ReForm”, an algorithm for the automated formalization of natural language industrial requirements into test cases. The system utilizes dependency rules like Part-of-Speech (POS) and Named Entity Recognition (NER) alongside semantic role labels (SRL).
• 11/2016 - 03/2019: Senior Engineer, Tata Elxsi Limited, Trivandrum, India
  • Maintained and updated MCAL Driver code for diverse Renesas micro-controllers in accordance with AUTOSAR standards on different communication protocols.

Publications

RAG-Ex: A Generic Framework for Explaining Retrieval Augmented Generation

Viju Sudhi, Sinchana Ramakanth Bhat, Max Rudat, and Roman Teucher. 2024. RAG-Ex: A Generic Framework for Explaining Retrieval Augmented Generation. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '24). Association for Computing Machinery, New York, NY, USA, 2776–2780. https://doi.org/10.1145/3626772.3657660

Illuminer: Instruction-tuned large language models as few-shot intent classifier and slot filler

Paramita Mirza, Viju Sudhi, Soumya Ranjan Sahoo, and Sinchana Ramakanth Bhat. 2024. ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot Filler. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 8639–8651, Torino, Italia. ELRA and ICCL.

CarExpert: Leveraging Large Language Models for In-Car Conversational Question Answering

Md Rashad Al Hasan Rony, Christian Suess, Sinchana Ramakanth Bhat, Viju Sudhi, Julia Schneider, Maximilian Vogel, Roman Teucher, Ken Friedl, and Soumya Sahoo. 2023. CarExpert: Leveraging Large Language Models for In-Car Conversational Question Answering. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 586–604, Singapore. Association for Computational Linguistics.

Natural Language Processing for Requirements Formalization: How to Derive New Approaches?

Sudhi, V., Kutty, L., Gröpler, R. (2023). Natural Language Processing for Requirements Formalization: How to Derive New Approaches?. In: Schlingloff, BH., Vogel, T., Skowron, A. (eds) Concurrency, Specification and Programming. Studies in Computational Intelligence, vol 1091. Springer, Cham. https://doi.org/10.1007/978-3-031-26651-5_1