The Impact of Chatbots Based on Large Language Models on Second Language Vocabulary Acquisition

To examine the impact of generative chatbots on Large Language Models on Second Language Vocabulary Acquisition. In this study, 52 English as a Foreign Language (EFL) students were randomly assigned to two groups: one with the assistance of a Chatbot based on Large Language Models and one without. Both groups learned the same series of target words over eight weeks. Post-treatment assessments, including systematic observation and quantitative tests assessing both receptive and productive vocabulary knowledge, were administered immediately after the study and again two weeks later. The findings demonstrate that employing an AI Chatbot based on Large Language Models significantly aids students in acquiring both receptive and productive vocabulary knowledge during their second language learning journey. Data pertain to the interactions with the chatbot, while assessment includes data from the pre-assessment, post-assessment, and delay assessment.

为探究基于大语言模型（Large Language Models）的生成式聊天机器人对第二语言词汇习得的影响。本研究将52名英语作为外语（English as a Foreign Language, EFL）的学生随机分为两组：一组使用基于大语言模型的聊天机器人辅助学习，另一组不使用该辅助工具。两组学生在为期八周的学习周期内均学习同一组目标词汇。本研究结束后即刻开展后测，并于两周后再次进行延迟复测，测试形式涵盖系统性观察以及评估接受性与产出性词汇知识的量化测试。研究结果表明，在第二语言学习过程中，使用基于大语言模型的AI聊天机器人可显著助力学生掌握接受性与产出性词汇知识。本数据集涵盖学生与聊天机器人的交互记录，以及前测、后测与延迟复测的相关评估数据。