通过任务中心化演化，让大模型更懂复杂指令
TaCIE: Enhancing Instruction Comprehension in Large Language Models through Task-Centred Instruction Evolution
- 将复杂指令拆解重组，动态生成更难更丰富的指令
- 多领域实验显示，微调后模型性能显著优于传统方法
- 适合需要精准指令理解的AI应用开发者
大语言模型（LLMs）在真实场景中需精准理解复杂指令以优化表现。随着对高质量指令微调数据的需求上升，传统仅演化简单初始指令的方法难以有效提升指令复杂度或跨领域难度控制。本文提出任务中心化指令演化（TaCIE），将指令演化从单一种子指令扩展为多元素动态组合。该方法先将复杂指令分解为基本组件，再生成新元素并融合原有成分，重新组装成逐步提升难度、多样性与复杂性的高级指令。在多个领域的实验中，使用这些演化指令微调的模型均显著优于传统方法，标志着指令驱动模型微调的重要进展。
原文摘要 · Abstract (English)
Large Language Models (LLMs) require precise alignment with complex instructions to optimize their performance in real-world applications. As the demand for refined instruction tuning data increases, traditional methods that evolve simple seed instructions often struggle to effectively enhance complexity or manage difficulty scaling across various domains. Our innovative approach, Task-Centered Instruction Evolution (TaCIE), addresses these shortcomings by redefining instruction evolution from merely evolving seed instructions to a more dynamic and comprehensive combination of elements. TaCIE starts by deconstructing complex instructions into their fundamental components. It then generates and integrates new elements with the original ones, reassembling them into more sophisticated instructions that progressively increase in difficulty, diversity, and complexity. Applied across multiple domains, LLMs fine-tuned with these evolved instructions have substantially outperformed those tuned with conventional methods, marking a significant advancement in instruction-based model fine-tuning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。