Saved in:
Bibliographic Details
Main Authors: Yuan, Haidong, Zhao, Haokun, Xu, Wanshi, Cao, Songjun, Zhou, Qingyu, Ma, Long, Fan, Hongjie
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.22542
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917433454886912
author Yuan, Haidong
Zhao, Haokun
Xu, Wanshi
Cao, Songjun
Zhou, Qingyu
Ma, Long
Fan, Hongjie
author_facet Yuan, Haidong
Zhao, Haokun
Xu, Wanshi
Cao, Songjun
Zhou, Qingyu
Ma, Long
Fan, Hongjie
contents Large language models (LLMs) often fail to meet the pedagogical needs of K-12 English learners in non-native contexts due to a proficiency mismatch. To address this widespread challenge, we introduce a proficiency-aligned framework that adapts LLM outputs to learner abilities, using China's national curriculum (CSE) as a representative case. Our framework enables precise control over lexical complexity through a four-tier grading system, supported by a comprehensive suite of new resources: graded vocabulary lists and a multi-turn dialogue corpus. Our core technical contribution is the \textbf{DDPO} algorithm,Diversity Driven Policy Optimization, a multi-turn GRPO-based approach designed to preserve dialogue diversity while holistically optimizing dialogue quality. This method significantly outperforms conventional approaches, achieving low out-of-vocabulary rates and high diversity while enhancing conversational naturalness and pedagogical value. While grounded in the CSE, our framework is designed for flexibility and can be readily adapted to other educational standards. Our models, data, and code will all be open-sourced, providing a scalable platform for personalized English speaking practice that effectively addresses the unique challenges faced by K-12 learners in non-immersive environments.
format Preprint
id arxiv_https___arxiv_org_abs_2604_22542
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Controllable Spoken Dialogue Generation: An LLM-Driven Grading System for K-12 Non-Native English Learners
Yuan, Haidong
Zhao, Haokun
Xu, Wanshi
Cao, Songjun
Zhou, Qingyu
Ma, Long
Fan, Hongjie
Computation and Language
Artificial Intelligence
Large language models (LLMs) often fail to meet the pedagogical needs of K-12 English learners in non-native contexts due to a proficiency mismatch. To address this widespread challenge, we introduce a proficiency-aligned framework that adapts LLM outputs to learner abilities, using China's national curriculum (CSE) as a representative case. Our framework enables precise control over lexical complexity through a four-tier grading system, supported by a comprehensive suite of new resources: graded vocabulary lists and a multi-turn dialogue corpus. Our core technical contribution is the \textbf{DDPO} algorithm,Diversity Driven Policy Optimization, a multi-turn GRPO-based approach designed to preserve dialogue diversity while holistically optimizing dialogue quality. This method significantly outperforms conventional approaches, achieving low out-of-vocabulary rates and high diversity while enhancing conversational naturalness and pedagogical value. While grounded in the CSE, our framework is designed for flexibility and can be readily adapted to other educational standards. Our models, data, and code will all be open-sourced, providing a scalable platform for personalized English speaking practice that effectively addresses the unique challenges faced by K-12 learners in non-immersive environments.
title Controllable Spoken Dialogue Generation: An LLM-Driven Grading System for K-12 Non-Native English Learners
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2604.22542