Assessing Fine-Tuning Efficacy in LLMs: A Case Study with Learning Guidance Chatbots

Rabia Bayraktar (), Batuhan Sarıtürk () and Merve Elmas Erdem ()

International Journal of Innovative Science and Research Technology (IJISRT), 2024, vol. 09, issue 05, 2461-2471

Abstract: Training and accurately evaluating task- specific chatbots is an important research area for Large Language Models (LLMs). These models can be developed for general purposes with the ability to handle multiple tasks, or fine-tuned for specific applications such as education or customer support. In this study, Mistral 7B, Llama-2 and Phi-2 models are utilized which have proven success on various benchmarks, including question answering. The models were fine-tuned using QLoRa with limited information gathered from course catalogs. The fine-tuned models were evaluated using various metrics, with the responses from GPT-4 taken as the ground truth. The experiments revealed that Phi-2 slightly outperformed Mistral 7B, achieving scores of 0.012 BLEU, 0.184 METEOR, and 0.873 BERT. Considering the evaluation metrics obtained, the strengths and weaknesses of known LLM models, the amount of data required for fine-tuning, and the effect of the fine-tuning method on model performance are discussed.

Keywords: LLM; Mistral; Llama; Phi; Fine-Tune; QLoRa. (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.ijisrt.com/assessing-finetuning-effica ... ng-guidance-chatbots (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cvr:ijisrt:2024:05:ijisrt24may1600

DOI: 10.38124/ijisrt/IJISRT24MAY1600

Access Statistics for this article

More articles in International Journal of Innovative Science and Research Technology (IJISRT) from IJISRT Publication
Bibliographic data for series maintained by Rahul Goyel ().