arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.13547cs.CL
收藏

ThinkNote: 通过建构主义认知建模增强大型语言模型的知识整合与利用

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

School of Computer Science and Engineering, Northeastern University(东北大学计算机科学与工程学院);Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系);Language Technologies Institute, Carnegie Mellon University(卡内基梅隆大学语言技术研究所)

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

AI总结:

ThinkNote通过建构主义认知建模提升大型语言模型的知识整合与利用能力,实验表明其在问答任务中优于基线方法。

摘要:

大型语言模型(LLMs)在广泛自然语言处理任务中表现出强大的性能。然而,当暴露于陌生外部信息时,它们往往表现出次优行为和不一致性,凸显了其在有效利用此类知识方面的局限性。受建构主义学习理论的启发,我们提出ThinkNote,一种新颖的框架,通过两阶段的建构主义认知建模过程增强LLMs的外部知识利用。具体而言,ThinkNote进行知识同化,将新信息与模型的参数记忆对齐,形成连贯的内部表示。然后应用思维适应,以适应内部推理,从而促进更一致和可靠的输出。广泛的实验结果表明,ThinkNote在各种问答基准测试中比强大的基线方法提高了10%。进一步分析表明,ThinkNote有效整合和利用外部知识,帮助LLMs生成准确的响应,并提高其自我一致性。所有数据和代码均可在https://github.com/OpenMatch/ThinkNote获取。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑