← 研踪 PaperTrailarXiv:2609.31568 · v2
DeepEdu-F: A Framework for Efficient and Scalable Agentic LLMs in Vietnamese Education
首次提交 2026-09-26 01:33
版本更新 2026-11-19 14:17
雷达观测 2026-11-20 19:58
摘要
Cloud AI assistants send student data to foreign servers, conflicting with data-sovereignty laws such as Vietnam's Decree 53, and are not grounded in the national curriculum, so they often hallucinate on local content. Self-hosting an open model keeps data on-premise but faces two costs that weight quantization does not remove. An AI tutoring session revisits the same long material every turn, so once prefix caching removes the prefill cost, decoding over a growing KV Cache dominates response time; and grounding the tutor in local knowledge by fine-tuning is too costly to repeat as that knowledge changes. We present DeepEdu-F, a framework for the Vietnamese AI tutor DeepEdu with two components. LastSet selects the critical KV Cache entries once per turn from the question's attention, decodes the whole turn from that set, and keeps the full cache so later questions can select again. REPAIR (Reliable Evidence-based Playbook Adaptation and Insight Revision) curates a verified playbook from past interactions instead of updating weights. LastSet decodes up to 3.1x faster than dense decoding at a 256k-token context, faster than four sparse baselines, with accuracy close to full attention. Compared with ACE (ADD), REPAIR raises final accuracy from 70.0% to 80.5% on Formula and from 53.6% to 59.7% on FiNER, while mean task/scenario goal completion across AppWorld's normal and challenge splits increases from 9.28% to 16.28%.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-19 14:17 · 最新观测版本
DeepEdu-F: A Framework for Efficient and Scalable Agentic LLMs in Vietnamese Education
Cloud AI assistants send student data to foreign servers, conflicting with data-sovereignty laws such as Vietnam's Decree 53, and are not grounded in the national curriculum, so they often hallucinate on local content. Self-hosting an open model keeps data on-premise but faces two costs that weight quantization does not remove. An AI tutoring session revisits the same long material every turn, so once prefix caching removes the prefill cost, decoding over a growing KV Cache dominates response time; and grounding the tutor in local knowledge by fine-tuning is too costly to repeat as that knowledge changes. We present DeepEdu-F, a framework for the Vietnamese AI tutor DeepEdu with two components. LastSet selects the critical KV Cache entries once per turn from the question's attention, decodes the whole turn from that set, and keeps the full cache so later questions can select again. REPAIR (Reliable Evidence-based Playbook Adaptation and Insight Revision) curates a verified playbook from past interactions instead of updating weights. LastSet decodes up to 3.1x faster than dense decoding at a 256k-token context, faster than four sparse baselines, with accuracy close to full attention. Compared with ACE (ADD), REPAIR raises final accuracy from 70.0% to 80.5% on Formula and from 53.6% to 59.7% on FiNER, while mean task/scenario goal completion across AppWorld's normal and challenge splits increases from 9.28% to 16.28%.
查看此版本解读 →查看此版本原文 ↗