Saved in:
Bibliographic Details
Main Authors: Wang, Song, Wang, Xun, Mei, Jie, Xie, Yujia, Muarray, Sean, Li, Zhang, Wu, Lingfeng, Chen, Si-Qing, Xiong, Wayne
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.15441
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Hallucination, a phenomenon where large language models (LLMs) produce output that is factually incorrect or unrelated to the input, is a major challenge for LLM applications that require accuracy and dependability. In this paper, we introduce a reliable and high-speed production system aimed at detecting and rectifying the hallucination issue within LLMs. Our system encompasses named entity recognition (NER), natural language inference (NLI), span-based detection (SBD), and an intricate decision tree-based process to reliably detect a wide range of hallucinations in LLM responses. Furthermore, we have crafted a rewriting mechanism that maintains an optimal mix of precision, response time, and cost-effectiveness. We detail the core elements of our framework and underscore the paramount challenges tied to response time, availability, and performance metrics, which are crucial for real-world deployment of these technologies. Our extensive evaluation, utilizing offline data and live production traffic, confirms the efficacy of our proposed framework and service.