AIDec 5, 2024

Bench-CoE: a Framework for Collaboration of Experts from Benchmark

arXiv:2412.04167v16 citationsh-index: 5Has Code
Originality Synthesis-oriented
AI Analysis

This is an incremental improvement for researchers and practitioners in AI, focusing on enhancing multi-task performance through expert collaboration.

The paper tackles the problem of optimizing performance across various tasks by enabling collaboration among LLM-driven experts using benchmark evaluations, and shows that the proposed Bench-CoE framework outperforms any single model in overall performance.

Large Language Models (LLMs) are key technologies driving intelligent systems to handle multiple tasks. To meet the demands of various tasks, an increasing number of LLMs-driven experts with diverse capabilities have been developed, accompanied by corresponding benchmarks to evaluate their performance. This paper proposes the Bench-CoE framework, which enables Collaboration of Experts (CoE) by effectively leveraging benchmark evaluations to achieve optimal performance across various tasks. Bench-CoE includes a set of expert models, a router for assigning tasks to corresponding experts, and a benchmark dataset for training the router. Moreover, we formulate Query-Level and Subject-Level approaches based on our framework, and analyze the merits and drawbacks of these two approaches. Finally, we conduct a series of experiments with vary data distributions on both language and multimodal tasks to validate that our proposed Bench-CoE outperforms any single model in terms of overall performance. We hope this method serves as a baseline for further research in this area. The code is available at \url{https://github.com/ZhangXJ199/Bench-CoE}.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes