Reading.help: Supporting EFL Readers with Proactive and On-Demand Explanation of English Grammar and Semantics

2025-05-20

AI Summary

EFL learners often struggle with reading comprehension in unsupervised settings due to insufficient teacher support. Method: This study designs and implements an LLM-driven intelligent reading assistance tool featuring a novel dual-mode explanation mechanism—“proactive prompting + on-demand triggering”—that generates real-time, grammar- and semantics-aware, context-sensitive interventions while enabling user-initiated deep explanations. The interface adopts behavior-guided interaction design, and prompt strategies and interaction logic are iteratively refined based on feedback from authentic EFL users. Contribution/Results: In an empirical study with Korean EFL readers, the tool significantly improved both accuracy and speed of independent reading comprehension under unsupervised conditions. It received unanimous endorsement from five learners and two education experts. The core contribution is a scalable, user-centered, dynamic explanation paradigm, offering a reusable technical pathway for autonomous language learning in resource-constrained environments.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

A large portion of texts in the world is written in English, but readers who see English as a Foreign Language (EFL) often struggle to read texts written in English accurately and swiftly. In many countries, EFL readers seek help from professional teachers and mentors, which is limited and costly. In this paper, we explore how an intelligent reading tool can assist EFL readers. To support our research agenda, we conducted a case study with EFL readers in South Korea. We at first developed an LLM-based reading tool based on prior literature. We then revised the tool based on the feedback from a study with 15 South Korean EFL readers. The final tool, named Reading.help, helps EFL readers comprehend complex sentences and paragraphs with on-demand and proactive explanations. We finally evaluated the tool with 5 EFL readers and 2 EFL education professionals. Our findings suggest Reading.help could potentially help EFL readers self-learn english when they do not have access to any external support.

Problem

• Assisting EFL readers with English grammar and semantics comprehension
• Providing proactive and on-demand explanations for complex texts
• Enabling self-learning for EFL readers without external support

Innovation

• LLM-based tool for EFL reading assistance
• Proactive and on-demand grammar explanations
• User feedback-driven iterative tool refinement