Fine-Tuning Large Language Models for Personality Development

Title

Fine-Tuning Large Language Models for Personality Development

Creator

Banerjee, Atmika M.; Mukhopadhyaya, Keka

Description

Large Language Models (LLMs) are state-of-the-art in Natural Language Processing (NLP) tasks but are extremely challenging to fine-tune with their size and computational needs. The current research targets the fine-tuning of the OpenLLaMA-3B model for personality development tasks with parameter-efficient fine-tuning (PEFT) via LoRA and QLoRA. To deal with hardware limitations, 4-bit quantization through BitsAndBytes was used, lowering memory without affecting accuracy. A FAISS-based Retrieval-Augmented Generation (RAG) pipeline was also used to improve contextual reliability. Semantic similarity (cosine similarity), BLEURT, ROUGE, and human evaluation were used to evaluate the model. The results of this experiment show that semantic similarity greatly increasing from 0% before fine-tuning to 80% after fine-tuning, demonstrating the benefit of PEFT and quantization in domain adaptation. The work illustrates that by leveraging effective fine-tuning, quantization, and retrieval augmentation, LLMs can be deployed at scale under limited resources while providing high contextual accuracy for personality development purposes. This approach not only enhances knowledge of the job, but it also has practical scalability for educational and self-improvement purposes. The findings highlight a viable path forward for applying small, yet strong, LLMs to personalized learning and adaptive human-AI interaction. 2025 IEEE.

Source

Proceedings of the 9th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2025;pp.2109-2116

Date

01-01-2025

Publisher

Institute of Electrical and Electronics Engineers Inc.

Subject

fine tuning; large language models; LoRA; parameter efficient fine tuning; personality development; QLoRA

Coverage

Banerjee A.M., Christ (Deemed to be University), Department of Cse, Bengaluru, India; Mukhopadhyaya K., Cmr Institute of Technology, Department of Ece, Bengaluru, India

Rights

Restricted Access; Hardcopy may be available in the library

Relation

ISBN: 979-833159929-4;

Format

online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1109/ICECA66444.2025.11382960

https://www.scopus.com/pages/publications/105034853925?origin=resultslist