Trustful LLMs: Customizing and Grounding Text Generation with knowledge bases and Dual Decoders

Xiaofeng Zhu, Jaya Krishna Mandivarapu


Abstract
Although people are impressed by the content generation skills of large language models, the use of LLMs, such as ChatGPT, is limited by the domain grounding of the content. The correctness and groundedness of the generated content need to be based on a verified context, such as results from Retrieval-Augmented Generation (RAG). One important issue when adapting LLMs to a customized domain is that the generated responses are often incomplete, or the additions are not verified and may even be hallucinated. Prior studies on hallucination detection have focused on evaluation metrics, which are not easily adaptable to dynamic domains and can be vulnerable to attacks like jail-breaking. In this work, we propose 1) a post-processing algorithm of leveraging knowledge triplets in RAG context to correct hallucinations and 2) a dual-decoder model that fuses RAG context to guide the generation process.
Anthology ID:
2024.customnlp4u-1.13
Volume:
Proceedings of the 1st Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U)
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Sachin Kumar, Vidhisha Balachandran, Chan Young Park, Weijia Shi, Shirley Anugrah Hayati, Yulia Tsvetkov, Noah Smith, Hannaneh Hajishirzi, Dongyeop Kang, David Jurgens
Venue:
CustomNLP4U
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
156–166
Language:
URL:
https://aclanthology.org/2024.customnlp4u-1.13
DOI:
Bibkey:
Cite (ACL):
Xiaofeng Zhu and Jaya Krishna Mandivarapu. 2024. Trustful LLMs: Customizing and Grounding Text Generation with knowledge bases and Dual Decoders. In Proceedings of the 1st Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U), pages 156–166, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Trustful LLMs: Customizing and Grounding Text Generation with knowledge bases and Dual Decoders (Zhu & Mandivarapu, CustomNLP4U 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.customnlp4u-1.13.pdf