Towards Optimizing and Evaluating a Retrieval Augmented QA Chatbot using LLMs with Human in the Loop

TL;DR

This paper presents the development and evaluation of a retrieval-augmented HR support chatbot using GPT-4, incorporating human-in-the-loop processes to enhance response quality and assess evaluation metrics.

Contribution

It introduces a human-in-the-loop methodology for optimizing a retrieval-augmented chatbot and demonstrates GPT-4's superior performance and reliable reference-free evaluation metrics.

Findings

GPT-4 outperforms other models in response quality.

Human-in-the-loop improves dataset and prompt quality.

Reference-free metrics align well with human evaluation.

Abstract

Large Language Models have found application in various mundane and repetitive tasks including Human Resource (HR) support. We worked with the domain experts of SAP SE to develop an HR support chatbot as an efficient and effective tool for addressing employee inquiries. We inserted a human-in-the-loop in various parts of the development cycles such as dataset collection, prompt optimization, and evaluation of generated output. By enhancing the LLM-driven chatbot's response quality and exploring alternative retrieval methods, we have created an efficient, scalable, and flexible tool for HR professionals to address employee inquiries effectively. Our experiments and evaluation conclude that GPT-4 outperforms other models and can overcome inconsistencies in data through internal reasoning capabilities. Additionally, through expert analysis, we infer that reference-free evaluation metrics such as G-Eval and Prometheus demonstrate reliability closely aligned with that of human evaluation.