GPT vs RETRO: Exploring the Intersection of Retrieval and Parameter-Efficient Fine-Tuning

Aleksander Ficek, Jiaqi Zeng, Oleksii Kuchaiev


Abstract
Parameter-Efficient Fine-Tuning (PEFT) and Retrieval-Augmented Generation (RAG) have become popular methods for adapting large language models while minimizing compute requirements. In this paper, we apply PEFT methods (P-tuning, Adapters, and LoRA) to a modified Retrieval-Enhanced Transformer (RETRO) and a baseline GPT model across several sizes, ranging from 823 million to 48 billion parameters. We show that RETRO models outperform GPT models in zero-shot settings due to their unique pre-training process but GPT models have higher performance potential with PEFT. Additionally, our study indicates that 8B parameter models strike an optimal balance between cost and performance and P-tuning lags behind other PEFT techniques. We further provide a comparative analysis of between applying PEFT to Instruction-tuned RETRO model and base RETRO model. This work presents the first comprehensive comparison of various PEFT methods integrated with RAG, applied to both GPT and RETRO models, highlighting their relative performance.
Anthology ID:
2024.emnlp-main.1081
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
19425–19432
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1081
DOI:
10.18653/v1/2024.emnlp-main.1081
Bibkey:
Cite (ACL):
Aleksander Ficek, Jiaqi Zeng, and Oleksii Kuchaiev. 2024. GPT vs RETRO: Exploring the Intersection of Retrieval and Parameter-Efficient Fine-Tuning. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 19425–19432, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
GPT vs RETRO: Exploring the Intersection of Retrieval and Parameter-Efficient Fine-Tuning (Ficek et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1081.pdf