Exploring Fact Memorization and Style Imitation in LLMs Using QLoRA: An Experimental Study and Quality Assessment Methods
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909223059718144 |
|---|---|
| author | Vyborov, Eugene Osypenko, Oleksiy Sotnyk, Serge |
| author_facet | Vyborov, Eugene Osypenko, Oleksiy Sotnyk, Serge |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08582 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploring Fact Memorization and Style Imitation in LLMs Using QLoRA: An Experimental Study and Quality Assessment Methods Vyborov, Eugene Osypenko, Oleksiy Sotnyk, Serge Computation and Language 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. |
| title | Exploring Fact Memorization and Style Imitation in LLMs Using QLoRA: An Experimental Study and Quality Assessment Methods |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.08582 |