Chain-of-Knowledge: Integrating Knowledge Reasoning into Large Language Models by Learning from Knowledge Graphs
This addresses the underexplored challenge of knowledge reasoning in LLMs for NLP applications, offering an incremental improvement by adapting knowledge graph techniques.
The paper tackles the problem of knowledge reasoning in large language models (LLMs) by introducing Chain-of-Knowledge, a framework that integrates knowledge graph reasoning through dataset construction and a trial-and-error learning mechanism, resulting in improved performance on knowledge reasoning and general reasoning benchmarks.
Large Language Models (LLMs) have exhibited impressive proficiency in various natural language processing (NLP) tasks, which involve increasingly complex reasoning. Knowledge reasoning, a primary type of reasoning, aims at deriving new knowledge from existing one.While it has been widely studied in the context of knowledge graphs (KGs), knowledge reasoning in LLMs remains underexplored. In this paper, we introduce Chain-of-Knowledge, a comprehensive framework for knowledge reasoning, including methodologies for both dataset construction and model learning. For dataset construction, we create KnowReason via rule mining on KGs. For model learning, we observe rule overfitting induced by naive training. Hence, we enhance CoK with a trial-and-error mechanism that simulates the human process of internal knowledge exploration. We conduct extensive experiments with KnowReason. Our results show the effectiveness of CoK in refining LLMs in not only knowledge reasoning, but also general reasoning benchmarkms.