Sinchana Ramakanth Bhat’s scientific contributions

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (2)


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

July 2024

·

31 Reads

·

8 Citations

·

Sinchana Ramakanth Bhat

·

Max Rudat

·


Figure 1: Illustration of a multi-turn in-car conversation between a user (in gray) and CarExpert (in blue).
Figure 2: High level overview of the CarExpert system architecture.
Figure 3: Semantic search during the inference (the vector space is depicted as a vector database for demonstration). The potential answer to the question is encapsulated in the box of retrieved document A.
Figure 5: Human-annotation tool used for extending training data.
Figure 6: An example multi-turn conversation between the user and CarExpert. The dialog starts with informal talk before starting the information-seeking question-answering.

+1

CarExpert: Leveraging Large Language Models for In-Car Conversational Question Answering
  • Conference Paper
  • Full-text available

January 2023

·

3 Reads

·

6 Citations

·

Christian Suess

·

Sinchana Ramakanth Bhat

·

[...]

·

Download

Citations (2)


... This comprehensive review categorizes existing research into architectures, training strategies, and applications, while also identifying persistent challenges and proposing future research directions aimed at enhancing the reliability and multilingual capabilities of RA-LLMs. Furthermore, RAG-Ex [20] introduces a model-agnostic framework that enhances the explainability of RAG systems, addressing the crucial need for transparency in AI outputs to foster user trust. Collectively, these studies reflect a growing emphasis on usability, explainability, and user engagement across various AI-driven environments. ...

Reference:

Cross-Format Retrieval-Augmented Generation in XR with LLMs for Context-Aware Maintenance Assistance
RAG-Ex: A Generic Framework for Explaining Retrieval Augmented Generation
  • Citing Conference Paper
  • July 2024

... Anticipating the presence of an LLM in such a vehicle could be used to improve, for instance, the passengers' in-car experience with better voice assistants processing even complex natural language-based dialogues between the human and the vehicle. In fact, some global automotive manufacturers are already working on deploying state-of-the-art foundational models within the vehicles to assist the in-car experience for passengers [6], [7]. ...

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