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

Source: [ThinkNote: Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modeling](<https://www.sota2.com/research/paper/68fa7bfb1e209131cea8b9cf>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-29T05:00:05.134Z

Authors: Zhipeng Xu, Zhenghao Liu, Yukun Yan, Shuo Wang, Shi Yu, Zheni Zeng, Chaojun Xiao, Zhiyuan Liu, Ge Yu, Chenyan Xiong

Published: 2024-02-21T06:04:53.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2402.13547>)

[PDF](<https://arxiv.org/pdf/2402.13547.pdf>)
