arXiv cs.CL· ai Team, Bowen Wu, Heng Wang, Jufeng Mi, Kang Liu, Kun Li, Ling Man, Long He, Suli Fan, Xiaosen Jiang, Yi Wang, Ying He, Yu Tang, Yunhan Li, Zifang Liu·· 11 小时前AI 评分26
Keepace.ai 发布面向运动健康领域的专用大模型 Keepace 技术报告
Keepace.ai: A Technical Report on a Large Language Model for Sports and Health
AI 导读
Keepace.ai 基于 Qwen3.5-27B 后训练推出运动健康领域专用大模型 Keepace，当前针对中文运动指导优化，覆盖训练计划生成、运动健康知识问答和个人运动数据分析三项任务。在领域专家设计的内部评分评测中，Keepace 优于其基座模型及更大的通用模型基线，在运动安全性、边界合规、结构化输出完整性和科学准确性上提升最明显。报告同时披露了数据管线与安全优先的评测框架。
正文 · 原文
Authors:Keepace.ai Team: Bowen Wu, Heng Wang, Jufeng Mi, Kang Liu, Kun Li, Ling Man, Long He, Suli Fan, Xiaosen Jiang, Yi Wang, Ying He, Yu Tang, Yunhan Li, Zifang Liu
Abstract:Large language models hold promise for delivering safe, scientifically grounded, and personalized exercise guidance at scale, yet the sports-and-health domain still lacks curated training corpora and rigorous evaluation benchmarks. Keepace (this http URL) is a domain-specialized LLM built on Qwen3.5-27B through post-training, currently optimized for Chinese-language exercise guidance across three tasks: workout plan generation, sports-and-health knowledge QA, and personal sports data analysis. In internal rubric-based evaluations designed with domain experts, Keepace outperforms its base model and larger general-purpose baselines, with the most pronounced improvements in exercise safety, boundary compliance, structured output completeness, and scientific accuracy. This report summarizes the current design, data pipeline, safety-first evaluation framework, and evaluation results of Keepace.
| Comments: | 21 pages, 3 figures, 13 tables. Technical report |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.38249 [cs.CL] |
| (or arXiv:2610.38249v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.38249 arXiv-issued DOI via DataCite |
Submission history
From: Bowen Wu [view email]
[v1]
Wed, 28 Oct 2026 04:00:29 UTC (1,022 KB)
[v2]
Fri, 30 Oct 2026 12:29:47 UTC (1,022 KB)
来源：arXiv cs.CL · arxiv.org