ThinkNote: Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modeling
This addresses the issue of inconsistent knowledge utilization in LLMs for NLP applications, representing an incremental improvement with a novel method.
The paper tackles the problem of large language models (LLMs) having suboptimal performance when using unfamiliar external knowledge, proposing ThinkNote to enhance knowledge integration and utilization, achieving a 10% improvement over baselines on question-answering benchmarks.
Large Language Models (LLMs) have demonstrated strong performance across a wide range of NLP tasks. However, they often exhibit suboptimal behaviors and inconsistencies when exposed to unfamiliar external information, underscoring their limitations in effectively leveraging such knowledge. Inspired by constructivist learning theory, we propose ThinkNote, a novel framework that enhances the external knowledge utilization of LLMs through a two-stage constructivist cognitive modeling process. Specifically, ThinkNote performs knowledge assimilation to align new information with the model's parametric memory, forming a coherent internal representation. It then applies thought accommodation to adapt internal reasoning, thereby promoting more consistent and reliable outputs. Extensive experimental results demonstrate that ThinkNote achieves a 10% improvement over strong baseline methods on various question-answering benchmarks. Further analysis indicates that ThinkNote effectively integrates and utilizes external knowledge to help LLMs generate accurate responses and improves their self-consistency. All data and codes are available at https://github.com/OpenMatch/ThinkNote.