Naive Bayes-based Context Extension for Large Language Models

Jianlin Su, Murtadha Ahmed, Bo Wen, Luo Ao, Mingren Zhu, Yunfeng Liu


Abstract
Large Language Models (LLMs) have shown promising in-context learning abilities. However, conventional In-Context Learning (ICL) approaches are often impeded by length limitations of transformer architecture, which pose challenges when attempting to effectively integrate supervision from a substantial number of demonstration examples. In this paper, we introduce a novel framework, called Naive Bayes-based Context Extension (NBCE), to enable existing LLMs to perform ICL with an increased number of demonstrations by significantly expanding their context size. Importantly, this expansion does not require fine-tuning or dependence on particular model architectures, all the while preserving linear efficiency. NBCE initially splits the context into equal-sized windows fitting the target LLM’s maximum length. Then, it introduces a voting mechanism to select the most relevant window, regarded as the posterior context. Finally, it employs Bayes’ theorem to generate the test task. Our experimental results demonstrate that NBCE substantially enhances performance, particularly as the number of demonstration examples increases, consistently outperforming alternative methods. The NBCE code will be made publicly accessible. The code NBCE is available at: https://github.com/amurtadha/NBCE-master
Anthology ID:
2024.naacl-long.431
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7791–7807
Language:
URL:
https://aclanthology.org/2024.naacl-long.431
DOI:
10.18653/v1/2024.naacl-long.431
Bibkey:
Cite (ACL):
Jianlin Su, Murtadha Ahmed, Bo Wen, Luo Ao, Mingren Zhu, and Yunfeng Liu. 2024. Naive Bayes-based Context Extension for Large Language Models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 7791–7807, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Naive Bayes-based Context Extension for Large Language Models (Su et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.431.pdf