TRACE-BN：将孟加拉语-英语辅导行为迁移至参数量小于10亿的离线语言模型

中文摘要 AI 辅助

孟加拉语-英语辅导不仅需要生成正确翻译，还需向学习者讲解语法差异、告知其可能出现的错误，并提供针对性练习。本文提出TRACE-BN，这是一个针对CEFR A1-A2级孟加拉语英语学习者的、由课程引导的结构化辅导轨迹数据集。每条轨迹包含词级注释、字面及自然翻译、孟加拉语语法解释、合理的学习者错误，以及带答案的针对性练习题。这些轨迹由Gemini 3.5 Flash Lite作为教师模型，从NCTB 9-10年级英语课程单元生成，随后经结构有效性、脚本完整性和语义重复过滤。我们使用4-bit量化的LoRA将所得结构化辅导行为迁移至Qwen3-0.6B，以实现资源受限场景下的离线部署。在保留的输入上，模式有效性从85.4%提升至95.8%；与教师模型参考相比，chrF++从15.28提升至34.77，BLEU从4.52提升至21.03。两名独立评审的领域级评估显示，翻译、语法解释、学习者错误诊断及练习匹配度均有提升，人工审核也验证了监督数据的质量。结果表明，在这些资源约束下，由课程引导的结构化监督可将多组件辅导行为迁移至参数量小于10亿的模型。该数据集、模型检查点和代码已在指定公开链接发布。

英文摘要

Bangla-English tutoring requires more than producing a correct translation: learners also need explanations of grammar differences, awareness of their likely errors, and targeted practice. We present TRACE-BN, a curriculum-guided dataset of structured tutoring traces for Bangla-speaking learners of English at the CEFR A1-A2 level. Each trace combines word-level glosses, literal and natural translations, Bangla grammar explanations, a plausible learner error, and a targeted practice question with its answer. The traces are generated by Gemini 3.5 Flash Lite as the teacher model from NCTB Classes 9-10 English curriculum units, then filtered for structural validity, script integrity, and semantic duplication. We transfer the resulting structured tutoring behavior to Qwen3-0.6B using LoRA with 4-bit quantization for resource-constrained offline deployment. On held-out inputs, schema validity increases from 85.4% to 95.8%, while, against teacher-model references, chrF++ improves from 15.28 to 34.77 and BLEU from 4.52 to 21.03. Field-level evaluation by two independent judges shows improvements across translation, grammar explanation, learner-error diagnosis, and practice alignment, while a human audit supports the quality of the supervision data. The results show that curriculum-guided structured supervision can transfer multi-component tutoring behavior to a sub-1B model under these resource constraints. The dataset, model checkpoints, and code are publicly available at https://huggingface.co/datasets/RaiyanKhaan/Trace-BN

发表机构

• North South University（北南大学）

机构由 AI 辅助整理，请以论文原文为准。