Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases

Jiarui Li, Ye Yuan, Zehua Zhang
3/15/2024
cs.CLcs.LG

No official code found. Best implementation: anlp-team/LTI_Neural_Navigator (45 stars, MIT, last commit 2024-03-18).

Abstract

We proposed an end-to-end system design towards utilizing Retrieval Augmented Generation (RAG) to improve the factual accuracy of Large Language Models (LLMs) for domain-specific and time-sensitive queries related to private knowledge-bases. Our system integrates RAG pipeline with upstream datasets processing and downstream performance evaluation. Addressing the challenge of LLM hallucinations, we finetune models with a curated dataset which originates from CMU's extensive resources and annotated with the teacher model. Our experiments demonstrate the system's effectiveness in generating more accurate answers to domain-specific and time-sensitive inquiries. The results also revealed the limitations of fine-tuning LLMs with small-scale and skewed datasets. This research highlights the potential of RAG systems in augmenting LLMs with external datasets for improved performance in knowledge-intensive tasks. Our code and models are available on Github.

View on arXivView PDF

Code Implementations(1)

anlp-team/LTI_Neural_NavigatorCommunity100%
MIT

"Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases" by Jiarui Li and Ye Yuan and Zehua Zhang

454HCL, HTMLFeb 17, 20242 years agoMIT
dataset-generationdatasetshallucinationlarge-language-modelsllama+6 more

Similar Papers

Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented Generation

90% match1 repo472025

DRAG: Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation

89% match2025

Systematic Knowledge Injection into Large Language Models via Diverse Augmentation for Domain-Specific RAG

89% match1 repo22025

Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely

89% match2024

WildHallucinations: Evaluating Long-form Factuality in LLMs with Real-World Entity Queries

88% match2024

Trustful LLMs: Customizing and Grounding Text Generation with Knowledge Bases and Dual Decoders

88% match2024

Cite this paper

@article{li2024enhancing,
  title  = {Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases},
  author = {Jiarui Li and Ye Yuan and Zehua Zhang},
  year   = {2024},
  eprint = {2403.10446},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.10446v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2403.10446.svg)](https://codeofpaper.com/paper/2403.10446)

Discussion