LangLingual: A Personalised, Exercise-oriented English Language Learning Tool Leveraging Large Language Models
Sammriddh Gupta, Sonit Singh, Aditya Joshi, Mira Kim
TL;DR
LangLingual addresses the challenge of delivering personalized, grammar-focused feedback at scale for English learners by integrating Large Language Models with the LangChain framework. The approach combines real-time feedback, context-aware exercise generation, and a hybrid proficiency assessment that fuses a word-bank-based signal with LLM judgments, expressed as $Level_{combined} = w_{wb} \cdot Level_{wb} + w_{llm} \cdot Level_{llm}$ with $w_{wb}=0.4$ and $w_{llm}=0.6$. Key contributions include data sources (Word Bank and Resources), a structured proficiency assessment, automated exercise generation, and a mechanism for identifying improvement areas during conversations; these are evaluated through survey-based and persona-based studies showing positive usability, engagement, and learning outcomes. The work demonstrates the potential of scalable, personalized English language learning tools and outlines practical avenues for future enhancements, such as CEFR alignment, proactive engagement, and gamified rewards to improve retention.
Abstract
Language educators strive to create a rich experience for learners, while they may be restricted in the extend of feedback and practice they can provide. We present the design and development of LangLingual, a conversational agent built using the LangChain framework and powered by Large Language Models. The system is specifically designed to provide real-time, grammar-focused feedback, generate context-aware language exercises and track learner proficiency over time. The paper discusses the architecture, implementation and evaluation of LangLingual in detail. The results indicate strong usability, positive learning outcomes and encouraging learner engagement.