arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.09168cs.CL
收藏

Explore-Instruct:通过主动探索增强特定领域的指令覆盖

Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration

Sun Yat-sen University(中山大学);Tencent AI Lab(腾讯人工智能实验室)

Fanqi Wan, Xinting Huang, Tao Yang, Xiaojun Quan, Wei Bi, Shuming Shi

AI总结:

本文提出Explore-Instruct方法,通过LLM主动探索和搜索算法生成多样化领域聚焦数据,有效提升特定领域指令覆盖并显著超越多个基线。

摘要:

指令微调可以通过增强多样性得到显著优化,使模型能够处理更广泛的任务范围。然而,用于此类微调的现有数据通常对各个领域的覆盖不足,限制了这些领域内细致理解和交互的范围。为解决这一缺陷,我们提出了Explore-Instruct,这是一种通过大型语言模型(LLMs)主动探索来增强特定领域指令微调数据覆盖的新方法。基于代表性的领域用例,Explore-Instruct通过实施搜索算法探索多种变体或可能性,以获取多样化和领域聚焦的指令微调数据。我们以数据为中心的分析验证了所提方法在改善特定领域指令覆盖方面的有效性。此外,我们模型的性能在多个基线上表现出显著进步,包括那些利用特定领域数据增强的基线。我们的发现为改善指令覆盖,特别是在特定领域背景下,提供了有希望的机会,从而推进了适应性语言模型的发展。我们的代码、模型权重和数据公开在 https://github.com/fanqiwan/Explore-Instruct。

英文摘要:

Instruction-tuning can be substantially optimized through enhanced diversity, resulting in models capable of handling a broader spectrum of tasks. However, existing data employed for such tuning often exhibit an inadequate coverage of individual domains, limiting the scope for nuanced comprehension and interactions within these areas. To address this deficiency, we propose Explore-Instruct, a novel approach to enhance the data coverage to be used in domain-specific instruction-tuning through active exploration via Large Language Models (LLMs). Built upon representative domain use cases, Explore-Instruct explores a multitude of variations or possibilities by implementing a search algorithm to obtain diversified and domain-focused instruction-tuning data. Our data-centric analysis validates the effectiveness of this proposed approach in improving domain-specific instruction coverage. Moreover, our model's performance demonstrates considerable advancements over multiple baselines, including those utilizing domain-specific data enhancement. Our findings offer a promising opportunity to improve instruction coverage, especially in domain-specific contexts, thereby advancing the development of adaptable language models. Our code, model weights, and data are public at \url{https://github.com/fanqiwan/Explore-Instruct}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑