Fine-Tuning and Retrieval Augmented Generation for Question Answering Using Affordable Large Language Models

Tiberiu Boros, Radu Chivereanu, Stefan Dumitrescu, Octavian Purcaru


Abstract
We present our proposed system named Sherlock to UNLP 2024 Shared Task on Question Answering winning first place. We employ a mix of methods, from using automatically translated datasets to perform supervised fine-tuning and direct preference optimization on instruction-tuned models, to model weight merging and retrieval augmented generation. We present and motivate our chosen sequence of steps, as well as an ablation study to understand the effect of each additional step. The resulting model and code are made publicly available (download links provided in the paper).
Anthology ID:
2024.unlp-1.10
Volume:
Proceedings of the Third Ukrainian Natural Language Processing Workshop (UNLP) @ LREC-COLING 2024
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Mariana Romanyshyn, Nataliia Romanyshyn, Andrii Hlybovets, Oleksii Ignatenko
Venue:
UNLP
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
75–82
Language:
URL:
https://aclanthology.org/2024.unlp-1.10
DOI:
Bibkey:
Cite (ACL):
Tiberiu Boros, Radu Chivereanu, Stefan Dumitrescu, and Octavian Purcaru. 2024. Fine-Tuning and Retrieval Augmented Generation for Question Answering Using Affordable Large Language Models. In Proceedings of the Third Ukrainian Natural Language Processing Workshop (UNLP) @ LREC-COLING 2024, pages 75–82, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Fine-Tuning and Retrieval Augmented Generation for Question Answering Using Affordable Large Language Models (Boros et al., UNLP 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2024.unlp-1.10.pdf