2024/04/29 by Bowen Xu, Shaoyu Wu, Xu, Bowen +5 · 3 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2404.18410
openalex publication_date 2024/04/29 · openalex created_date 2024/05/11 · openalex updated_date 2026/07/28
With the proliferation of large language models (LLMs), the comprehensive alignment of such models across multiple tasks has emerged as a critical area of research. Existing alignment methodologies primarily address single task, such as multi-turn dialogue, coding, mathematical problem-solving, and tool usage. Although there is a large amount of high-quality data available for those tasks, most of them provide only questions and answers without including the system prompt. Though a detailed analysis of the Qwen language model, we found that the system prompt has a significant impact on both training and inference processes of LLM. We attributes this phenomenon to overfitting to the system prompt. In address this issue, we introduce a novel technique termed Mixture-of-Instructions (MoI), which employs a strategy of instruction packing combined with diverse system prompts to boost the alignment efficiency of language models. We have also compiled a diverse set of seven benchmark datasets to rigorously evaluate the alignment efficacy of the MoI-enhanced language model. Our methodology was applied to the open-source Qwen-7B-chat model, culminating in the development of Qwen-SFT-MoI. This enhanced model demonstrates significant advancements in generative capabilities across coding, mathematics, and tool use tasks.