Towards Optimizing and Evaluating a Retrieval Augmented QA Chatbot using LLMs with Human-in-the-Loop.
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 LLMdriven 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 GEval and Prometheus demonstrate reliability closely aligned with that of human evaluation
| Attribute | Value |
|---|---|
| Address | |
| Authors | Anum Afzal , Florian Matthes |
| Citation | @inproceedings{afzal-etal-2024-towards, title = "Towards Optimizing and Evaluating a Retrieval Augmented {QA} Chatbot using {LLM}s with Human-in-the-Loop", author = "Afzal, Anum and Kowsik, Alexander and Fani, Rajna and Matthes, Florian", editor = "Dragut, Eduard and Li, Yunyao and Popa, Lucian and Vucetic, Slobodan and Srivastava, Shashank", booktitle = "Proceedings of the Fifth Workshop on Data Science with Human-in-the-Loop (DaSH 2024)", month = jun, year = "2024", address = "Mexico City, Mexico", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.dash-1.2", doi = "10.18653/v1/2024.dash-1.2", pages = "4--16", 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.", } |
| Key | |
| Research project | Abstractive Text Summarization for Domain-Specific Documents (ATESD) |
| Title | Towards Optimizing and Evaluating a Retrieval Augmented QA Chatbot using LLMs with Human-in-the-Loop. |
| Type of publication | Workshop |
| Year | 2024 |
| Publication URL | https://aclanthology.org/2024.dash-1.2/ |
| Acronym | |
| Project | |
| Team members |