让大模型通过提问对话主动学习，效果比被动接收提升25%。
INTERACT: Enabling Interactive, Question-Driven Learning in Large Language Models
- 学生模型通过反复提问与教师模型对话获取知识
- 仅5轮对话即可让弱初始模型达到静态学习水平，最高提升25%
- 适合希望提升模型泛化能力的研究者和开发者
大型语言模型（LLMs）擅长回答问题，但仍是被动学习——只能吸收静态数据，无法主动质疑与修正知识。本文探索如何通过师生对话使LLM实现交互式、问题驱动的学习。我们提出INTERACT（INTERactive learning for Adaptive Concept Transfer）框架，其中‘学生’模型通过迭代提问从‘教师’模型获取知识，覆盖1,347个不同场景，包括歌词、新闻、电影剧情、学术论文和图像。实验表明，在多种任务和模型架构下，交互学习显著提升性能，最高达25%的增益；‘冷启动’学生模型在仅五轮对话后即能匹配静态学习基线。此外，该方法还能缓解教师模型较弱带来的劣势，体现问题驱动学习的鲁棒性。
原文摘要 · Abstract (English)
Large language models (LLMs) excel at answering questions but remain passive learners-absorbing static data without the ability to question and refine knowledge. This paper explores how LLMs can transition to interactive, question-driven learning through student-teacher dialogues. We introduce INTERACT (INTERactive learning for Adaptive Concept Transfer), a framework in which a "student" LLM engages a "teacher" LLM through iterative inquiries to acquire knowledge across 1,347 contexts, including song lyrics, news articles, movie plots, academic papers, and images. Our experiments show that across a wide range of scenarios and LLM architectures, interactive learning consistently enhances performance, achieving up to a 25% improvement, with 'cold-start' student models matching static learning baselines in as few as five dialogue turns. Interactive setups can also mitigate the disadvantages of weaker teachers, showcasing the robustness of question-driven learning.
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。