Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models

Keming Lu, Hongyi Yuan, Runji Lin, Junyang Lin, Zheng Yuan, Chang Zhou, Jingren Zhou


Abstract
The complementary potential of Large Language Models (LLM) assumes off-the-shelf LLMs have heterogeneous expertise in a wide range of domains and tasks so that an ensemble of LLMs can achieve consistently better performance. Existing ensemble methods for LLMs mainly focus on reward model ranking of outputs, leading to significant computation overhead. To combat this issue, we revisit the complementary potential of LLMs and further elaborate on it by mining latent expertise with off-the-shelf reward models. We propose ZOOTER, a reward-guided routing method distilling rewards on training queries to train a routing function, which can precisely distribute each query to the LLM with expertise about it. We also integrate a tag-based label enhancement to mitigate noise from uncertainty when using rewards as silver supervision. ZOOTER shows computation efficiency in inference as it only introduces minor computation overhead of a routing function compared with reward model ranking methods. We evaluate ZOOTER on a comprehensive benchmark collection with 26 subsets in different domains and tasks. ZOOTER outperforms the best single model on average and ranks first on 44% of tasks, even surpassing multiple reward model ranking methods.
Anthology ID:
2024.naacl-long.109
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:
1964–1974
Language:
URL:
https://aclanthology.org/2024.naacl-long.109
DOI:
10.18653/v1/2024.naacl-long.109
Bibkey:
Cite (ACL):
Keming Lu, Hongyi Yuan, Runji Lin, Junyang Lin, Zheng Yuan, Chang Zhou, and Jingren Zhou. 2024. Routing to the Expert: Efficient Reward-guided Ensemble of 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 1964–1974, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models (Lu et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.109.pdf