MUFFIN：策划多面向指令以提升指令遵循能力
MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following
AI总结：
MUFFIN通过为每个输入自动扩展多样化的任务来策划指令遵循数据集，在四个零样本基准上显著提升了不同规模LLM的指令遵循能力。
摘要：
在大型语言模型（LLM）领域，提升指令遵循能力通常涉及策划大规模的训练数据。这通过两种主要方案实现：i) 缩放输入：针对每个任务指令扩充（输入，输出）对，旨在更好地遵循指令。ii) 缩放无输入任务：扩充任务，每个任务由（指令，输出）对组成（不再需要单独的输入）。然而，在缩放输入方案下，LLM往往对输入过度敏感，导致误解指令或不遵守指令。相反，缩放无输入任务需要大量任务，但在处理缩放输入方案中的实例时，指令遵循效果较差。本研究引入了MUFFIN，一种新的指令遵循数据集策划方案。具体而言，我们通过多样化的输入面向自动为每个输入扩展任务。在四个零样本基准上的实验结果表明，不同规模的LLM在MUFFIN上训练后，通常比在上述两种方案上训练的模型展现出更优越的指令遵循能力。
英文摘要：
In the realm of large language models (LLMs), enhancing instruction-following capability often involves curating expansive training data. This is achieved through two primary schemes: i) Scaling-Inputs: Amplifying (input, output) pairs per task instruction, aiming for better instruction adherence. ii) Scaling Input-Free Tasks: Enlarging tasks, each composed of an (instruction, output) pair (without requiring a separate input anymore). However, LLMs under Scaling-Inputs tend to be overly sensitive to inputs, leading to misinterpretation or non-compliance with instructions. Conversely, Scaling Input-Free Tasks demands a substantial number of tasks but is less effective in instruction following when dealing with instances in Scaling-Inputs. This work introduces MUFFIN, a new scheme of instruction-following dataset curation. Specifically, we automatically Scale Tasks per Input by diversifying these tasks with various input facets. Experimental results across four zero-shot benchmarks, spanning both Scaling-Inputs and Scaling Input-Free Tasks schemes, reveal that LLMs, at various scales, trained on MUFFIN generally demonstrate superior instruction-following capabilities compared to those trained on the two aforementioned schemes.
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。
