CLJun 12, 2024
Exploring Fact Memorization and Style Imitation in LLMs Using QLoRA: An Experimental Study and Quality Assessment Methods
arXiv:2406.08582v11 citations
Originality Synthesis-oriented
AI Analysis
This work addresses domain adaptation for LLMs, but it is incremental as it applies an existing method (QLoRA) to a specific simulation task.
The study explored adapting large language models using QLoRA to simulate human interview responses, assessing quality through style imitation and fact memorization metrics.
There are various methods for adapting LLMs to different domains. The most common methods are prompting, finetuning, and RAG. In this work, we explore the possibility of adapting a model using one of the PEFT methods - QLoRA. The experiment aims to simulate human responses based on their interviews. The simulation quality is assessed by comparing the quality of the style and the quality of the generated facts.