MultiInstruct: 通过指令微调改进多模态零样本学习
MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning
AI总结：
本研究提出首个多模态指令微调基准数据集MultiInstruct，基于OFA模型结合迁移学习策略，提升了多模态零样本性能，并设计敏感度指标验证了多任务微调对降低指令变体敏感度的作用。
摘要：
指令微调是一种在通过指令指定的任务上微调预训练语言模型的新型学习范式，已在各类自然语言处理任务上展现出可观的零样本性能，但尚未在视觉和多模态任务中得到探索。本研究提出了MUL-TIINSTRUCT，这是首个多模态指令微调基准数据集，包含62种不同的多模态任务，采用统一的序列到序列格式，覆盖10个大类。这些任务源自21个现有开源数据集，每个任务配有5条专家撰写的指令。我们以OFA作为多模态指令微调的基础预训练模型，为进一步提升其零样本性能，探索了多种迁移学习策略以利用大规模NATURAL INSTRUCTIONS数据集。实验结果表明，模型在各类未见过的多模态任务上具备出色的零样本性能，也验证了从纯文本指令数据集进行迁移学习的优势。我们还设计了一种新的评估指标——敏感度（Sensitivity），用于评估模型对指令多样性的敏感程度。结果显示，在多样化的任务和指令集合上微调模型，会降低模型对每个任务的指令变体的敏感度。
英文摘要：
Instruction tuning, a new learning paradigm that fine-tunes pre-trained language models on tasks specified through instructions, has shown promising zero-shot performance on various natural language processing tasks. However, it has yet to be explored for vision and multimodal tasks. In this work, we introduce MUL-TIINSTRUCT, the first multimodal instruction tuning benchmark dataset that consists of 62 diverse multimodal tasks in a unified seq-to-seq format covering 10 broad categories. The tasks are derived from 21 existing open-source datasets and each task is equipped with 5 expert-written instructions. We take OFA as the base pre-trained model for multimodal instruction tuning, and to further improve its zero-shot performance, we explore multiple transfer learning strategies to leverage the large-scale NATURAL INSTRUCTIONS dataset. Experimental results demonstrate strong zero-shot performance on various unseen multimodal tasks and the benefit of transfer learning from a text-only instruction dataset. We also design a new evaluation metric - Sensitivity, to evaluate how sensitive the model is to the variety of instructions. Our results indicate that fine-tuning the model on a diverse set of tasks and instructions leads to a reduced sensitivity to variations in instructions for each task.
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。
