用动态知识库让大模型快速学会新任务，不丢旧知识。
KnowMap: Efficient Knowledge-Driven Task Adaptation for LLMs
- 从环境与经验数据构建动态知识库，小模型嵌入知识后赋能大模型。
- 在ScienceWorld上使gpt-4-turbo性能提升17.71%。
- 适合需要快速适配新任务且怕遗忘的场景，如智能助手、专业领域应用。
大型语言模型（LLMs）虽具备强大的开放世界任务能力，但在快速适应新专业任务时面临挑战，因其依赖静态预训练知识。传统微调方法成本高、数据需求大，易引发“灾难性遗忘”。为此，我们提出KnowMap，一种从环境与经验数据中动态构建知识库的新方法。KnowMap通过微调一个小型知识嵌入模型，将任务特定知识注入大型LLM。在ScienceWorld基准上的实验表明，该方法使gpt-4-turbo模型性能提升17.71%。KnowMap不仅为大模型任务适应提供高效方案，还揭示了融合环境与经验知识可增强其推理能力。
原文摘要 · Abstract (English)
While Large Language Models (LLMs) possess significant capabilities in open-world agent tasks, they also face challenges in rapidly adapting to new, specialized tasks due to their reliance on static pre-trained knowledge. Traditional methods such as fine-tuning are often costly, data-intensive, and may lead to "catastrophic forgetting." Therefore, we present KnowMap, a novel approach that dynamically constructs a knowledge base from environmental and experiential data. KnowMap fine-tunes a small knowledge-embedding model to equip a larger LLM with valuable task-specific knowledge. Our experiments on the ScienceWorld benchmark demonstrate 17.71% improvement for the performance of gpt-4-turbo model. KnowMap not only provides an efficient and effective means for LLM task-adapting, but also highlights how integrating environmental and experiential knowledge can enhance LLMs' reasoning capabilities.
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。