{"ID":2835134,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.00380","arxiv_id":"2512.00380","title":"Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study","abstract":"In low-resource framework development (e.g., HarmonyOS), large language models (LLMs) often lack sufficient pre-training exposure, resulting in poor code generation performance. Although they generally preserve programming logic across languages, they frequently fail on framework-specific APIs and syntax, revealing a gap between learned algorithmic knowledge and unfamiliar framework conventions. Consequently, even advanced models such as GPT-4o struggle to produce correct code without prior exposure. Inspired by these challenges, we propose APIKG4Syn, a framework that leverages API knowledge graphs to synthesize API-oriented question-code pairs without requiring executable environments. It incorporates both single-API and multi-API information, with the latter guided by uncertainty estimation (UE) and Monte Carlo Tree Search (MCTS), to construct high-quality fine-tuning data. For evaluation, we select HarmonyOS as a case study due to its accessible documentation and growing ecosystem, and build the first benchmark for its code generation. Experimental results show that fine-tuning Qwen2.5-Coder-7B with APIKG4Syn achieves a pass@1 of 25.00%, outperforming untuned GPT-4o (17.59%). We further observe that larger volumes of data generated by APIKG4Syn consistently lead to better fine-tuning performance, and that the optimal Single-API to Multi-API ratio is 8:2. Ablation studies also confirm the necessity and effectiveness of each component in our framework. These findings highlight the effectiveness of API-oriented data in enhancing LLM performance for low-resource software development scenarios.","short_abstract":"In low-resource framework development (e.g., HarmonyOS), large language models (LLMs) often lack sufficient pre-training exposure, resulting in poor code generation performance. Although they generally preserve programming logic across languages, they frequently fail on framework-specific APIs and syntax, revealing a g...","url_abs":"https://arxiv.org/abs/2512.00380","url_pdf":"https://arxiv.org/pdf/2512.00380v3","authors":"[\"Mingwei Liu\",\"Zheng Pei\",\"Yanlin Wang\",\"Zihao Wang\",\"Zikang Li\",\"Enci Lin\",\"Xin Peng\",\"Zibin Zheng\"]","published":"2025-11-29T08:13:54Z","proceeding":"cs.SE","tasks":"[\"cs.SE\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}