• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. CarExpert: Leveraging Large Language Models for In-Car Conversational Question Answering
 
  • Details
  • Full
Options
October 14, 2023
Poster
Title

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

Title Supplement
Poster presented at EMNLP 2023, Conference on Empirical Methods in Natural Language Processing, December 6-10, 2023, Singapore
Abstract
Large language models (LLMs) have demonstrated remarkable performance by following natural language instructions without finetuning them on domain-specific tasks and data. However, leveraging LLMs for domain-specific question answering suffers from severe limitations. The generated answer tends to hallucinate due to the training data collection time (when using off-the-shelf), complex user utterance and wrong retrieval (in retrievalaugmented generation). Furthermore, due to the lack of awareness about the domain and expected output, such LLMs may generate unexpected and unsafe answers that are not tailored to the target domain. In this paper, we propose CarExpert, an in-car retrieval-augmented conversational question-answering system leveraging LLMs for different tasks. Specifically, CarExpert employs LLMs to control the input, provide domain-specific documents to the extractive and generative answering components, and controls the output to ensure safe and domain-specific answers. A comprehensive empirical evaluation exhibits that CarExpert outperforms state-of-the-art LLMs in generating natural, safe and car-specific answers.
Author(s)
Rony, Md Rashad Al Hasan
BMW Group  
Süß, Christian
BMW Group  
Bhat, Sinchana Ramakanth
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Sudhi, Viju
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Schneider, Julia
ONSEI GmbH
Vogel, Maximilian
BIG PICTURE GmbH
Teucher, Roman  
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Friedl, Ken E.
BMW Group  
Sahoo, Soumya Ranjan  
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Conference
Conference on Empirical Methods in Natural Language Processing 2023  
Open Access
File(s)
Download (670.71 KB)
Rights
CC BY 4.0: Creative Commons Attribution
DOI
10.24406/publica-2245
Language
English
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024