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

Anum Afzal, Alexander Kowsik, Rajna Fani, Florian Matthes


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 a large multinational company 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.
Anthology ID:
2024.dash-1.2
Volume:
Proceedings of the Fifth Workshop on Data Science with Human-in-the-Loop (DaSH 2024)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Eduard Dragut, Yunyao Li, Lucian Popa, Slobodan Vucetic, Shashank Srivastava
Venues:
DaSH | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4–16
Language:
URL:
https://aclanthology.org/2024.dash-1.2
DOI:
10.18653/v1/2024.dash-1.2
Bibkey:
Cite (ACL):
Anum Afzal, Alexander Kowsik, Rajna Fani, and Florian Matthes. 2024. Towards Optimizing and Evaluating a Retrieval Augmented QA Chatbot using LLMs with Human-in-the-Loop. In Proceedings of the Fifth Workshop on Data Science with Human-in-the-Loop (DaSH 2024), pages 4–16, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Towards Optimizing and Evaluating a Retrieval Augmented QA Chatbot using LLMs with Human-in-the-Loop (Afzal et al., DaSH-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.dash-1.2.pdf