专家模型还是通用模型？面向特定NLP任务的指令微调
Specialist or Generalist? Instruction Tuning for Specific NLP Tasks
AI总结：
本文研究了在构建特定NLP任务的专家模型时引入通用指令微调的效果，发现其在任务覆盖广或数据有限时提升性能并增强理解推理能力，但含幻觉的通用数据会损害事实知识任务表现。
摘要：
大型语言模型（LLMs）同时执行广泛自然语言处理（NLP）任务的潜力一直受到广泛研究。尽管指令微调已被证明是将LLMs转化为此类通用模型的数据高效方法，但其性能仍落后于专门针对特定任务训练的专家模型。本文研究引入广泛覆盖的通用指令微调是否有助于构建专家模型。我们假设其有效性取决于任务特异性和技能要求。我们的实验评估了四个具有不同覆盖水平的目标任务，结果表明，当任务覆盖范围广泛时，集成通用指令微调能持续提升模型性能。当特定任务的训练数据量有限时，这种效果尤为显著。对聚焦于不同能力的三个目标任务的进一步研究表明，通用指令微调能提升理解和推理能力。然而，对于需要事实知识的任务，包含幻觉信息的通用数据可能会对模型性能产生负面影响。总体而言，我们的工作为利用通用指令微调开发专家模型提供了系统性指南。代码及相关资源见 https://github.com/DavidFanzz/Generalist_or_Specialist。
英文摘要：
The potential of large language models (LLMs) to simultaneously perform a wide range of natural language processing (NLP) tasks has been the subject of extensive research. Although instruction tuning has proven to be a data-efficient method for transforming LLMs into such generalist models, their performance still lags behind specialist models trained exclusively for specific tasks. In this paper, we investigate whether incorporating broad-coverage generalist instruction tuning can contribute to building a specialist model. We hypothesize that its efficacy depends on task specificity and skill requirements. Our experiments assess four target tasks with distinct coverage levels, revealing that integrating generalist instruction tuning consistently enhances model performance when the task coverage is broad. The effect is particularly pronounced when the amount of task-specific training data is limited. Further investigation into three target tasks focusing on different capabilities demonstrates that generalist instruction tuning improves understanding and reasoning abilities. However, for tasks requiring factual knowledge, generalist data containing hallucinatory information may negatively affect the model's performance. Overall, our work provides a systematic guide for developing specialist models with general instruction tuning. Our code and other related resources can be found at https://github.com/DavidFanzz/Generalist_or_Specialist.
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。
