MoAA-SFT

This is the SFT data of our MoAA method described in this [paper](https://arxiv.org/abs/2505.03059). We subsample from two widely-used open-source instruction tuning datasets: UltraFeedback and UltraChat. Our subsampling strategy involves utilizing the entire UltraFeedback dataset and randomly selecting 5,000 samples from UltraChat. We use MoA to generate responses. The proposers used in our study are WizardLM-2-8x22b, Gemma-2-7b-it, Qwen-2-72b-Instruct, and Llama-3.1-70b-Instruct, while Qwen-1.5-110b-Instruct serves as the aggregator. ## Citation ``` @article{wang2025improving, title = {Improving Model Alignment Through Collective Intelligence of Open-Source LLMS}, author = {Junlin Wang and Roy Xie and Shang Zhu and Jue Wang and Ben Athiwaratkun and Bhuwan Dhingra and Shuaiwen Leon Song and Ce Zhang and James Zou}, year = {2025}, journal = {arXiv preprint arXiv: 2505.03059} } ```