ThinkNote: Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modeling

TL;DR

ThinkNote introduces a constructivist-inspired framework that significantly improves large language models' ability to integrate and utilize external knowledge, leading to more consistent and accurate responses across NLP tasks.

Contribution

It proposes a novel two-stage cognitive modeling approach inspired by constructivist theory to enhance external knowledge utilization in LLMs.

Findings

Achieves 10% improvement on question-answering benchmarks

Enhances model consistency and knowledge integration

Demonstrates effective external knowledge utilization

Abstract

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.