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

Anum Afzal, Alexander Kowsik, Rajna Fani, Florian Matthes

Publikation: KonferenzbeitragPapierBegutachtung

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.
OriginalspracheEnglisch (Amerika)
Seiten4–16
PublikationsstatusEingereicht - 8 Juli 2024
VeranstaltungProceedings of the Fifth Workshop on Data Science with Human-in-the-Loop - Mexico City, Mexiko
Dauer: 20 Juni 2024 → …
https://aclanthology.org/2024.dash-1

Konferenz

KonferenzProceedings of the Fifth Workshop on Data Science with Human-in-the-Loop
KurztitelDaSH
Land/GebietMexiko
OrtMexico City
Zeitraum20/06/24 → …
Internetadresse

Fingerprint

Untersuchen Sie die Forschungsthemen von „Towards Optimizing and Evaluating a Retrieval Augmented QA Chatbot using LLMs with Human-in-the-Loop“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren