arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.14293cs.CL
收藏

利用大型语言模型实现NLP教育中的概念图恢复与问答

Leveraging Large Language Models for Concept Graph Recovery and Question Answering in NLP Education

University of Tokyo(东京大学);Smartor Inc.(思玛特公司);Yale University(耶鲁大学);INRIA(法国国家信息与自动化研究所);Duke-NUS Medical School(杜克-新加坡国立大学医学院)

Rui Yang, Boming Yang, Sixun Ouyang, Tianwei She, Aosong Feng, Yuang Jiang, Freddy Lecue, Jinghui Lu, Irene Li

AI总结:

本文研究大型语言模型在NLP教育中的概念图恢复与问答能力,提出经专家验证的TutorQA基准和结合概念图的CGLLM流水线,在零样本概念图恢复和问答任务上均取得显著F1提升。

摘要:

在自然语言处理(NLP)领域,大型语言模型(LLMs)已在文本生成任务中展现出潜力。然而,它们在教育应用方面,尤其是针对特定领域查询的应用,仍未得到充分探索。本研究考察了LLMs在教育场景中的能力,重点关注概念图恢复和问答(QA)。我们评估了LLMs在创建特定领域概念图时的零样本性能,并引入了TutorQA,这是一个新的、经专家验证的、以NLP为重点的科学图推理与问答基准。TutorQA包含五个任务,共500个问答对。为解决TutorQA中的查询问题,我们提出了CGLLM,这是一种将概念图与LLMs相结合以回答多样化问题的流水线。我们的结果表明,LLMs的零样本概念图恢复性能可与监督学习方法相媲美,平均F1分数提高了3%。在TutorQA任务中,LLMs的F1分数提升最高可达26%。此外,人工评估和分析表明,CGLLM生成的答案包含更细粒度的概念。

英文摘要:

In the domain of Natural Language Processing (NLP), Large Language Models (LLMs) have demonstrated promise in text-generation tasks. However, their educational applications, particularly for domain-specific queries, remain underexplored. This study investigates LLMs' capabilities in educational scenarios, focusing on concept graph recovery and question-answering (QA). We assess LLMs' zero-shot performance in creating domain-specific concept graphs and introduce TutorQA, a new expert-verified NLP-focused benchmark for scientific graph reasoning and QA. TutorQA consists of five tasks with 500 QA pairs. To tackle TutorQA queries, we present CGLLM, a pipeline integrating concept graphs with LLMs for answering diverse questions. Our results indicate that LLMs' zero-shot concept graph recovery is competitive with supervised methods, showing an average 3% F1 score improvement. In TutorQA tasks, LLMs achieve up to 26% F1 score enhancement. Moreover, human evaluation and analysis show that CGLLM generates answers with more fine-grained concepts.

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。

↑