KnowMap: Efficient Knowledge-Driven Task Adaptation for LLMs
This addresses the challenge of efficient task adaptation for LLMs, offering a solution that is less costly and data-intensive than traditional fine-tuning, though it appears incremental in its approach.
The paper tackles the problem of LLMs struggling to adapt to new specialized tasks due to static pre-trained knowledge, and it presents KnowMap, which dynamically constructs a knowledge base to improve performance, achieving a 17.71% improvement on the ScienceWorld benchmark.
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.