AI 中文总结
本研究通过微调小型语言模型（SLM）并搭配后处理器VASPGuard构建INCAR-SLM，在INCARBench上优于通用大模型，证明小型模型经适配可可靠生成VASP INCAR文件，适配后性能随规模增长趋于饱和。
AI 中文摘要
语言模型可根据自然语言请求生成VASP INCAR文件，但目前仅大型专有云模型能可靠处理紧密耦合、对物理参数敏感的设置，这种依赖与本地高通量材料工作流（注重隐私、成本和离线部署）不匹配。本文表明小型语言模型（SLM）可缩小这一差距：该SLM基于参考VASP计算进行微调，并搭配确定性后处理器VASPGuard（用于检查语法、工作流及材料相关约束），组合模型名为INCAR-SLM。在VASP INCAR生成基准INCARBench上，基于Qwen3-4B的INCAR-SLM优于所有评估的通用大语言模型，在100分制INCAR得分上超过GPT-5.4达15.55分。该提升主要来自微调，VASPGuard用于修正剩余错误。进一步发现模型规模影响低于预期：应用微调与后处理后，性能在数十亿参数时趋于饱和，Qwen3-4B优于同系列更大模型。
英文摘要
Language models can prepare VASP INCAR files from natural-language requests, but so far only large proprietary cloud models come close to handling the tightly coupled, physics-sensitive settings reliably, a dependence that fits poorly with local, high-throughput materials workflows where privacy, cost, and offline deployment matter. We show that a small language model (SLM) can close this gap. The SLM is fine-tuned on reference VASP calculations and paired with VASPGuard, a deterministic post-processor that checks syntax, workflow, and material-dependent constraints; we call the combined model INCAR-SLM. On INCARBench, a benchmark for VASP INCAR generation, INCAR-SLM built on Qwen3-4B outperforms every general-purpose LLM evaluated, exceeding GPT-5.4 by 15.55 points on the 100-point INCAR Score. Most of this gain comes from fine-tuning, with VASPGuard correcting the errors that remain. We further find that model size matters less than expected: once fine-tuning and post-processing are applied, performance saturates at a few billion parameters, and Qwen3-4B outperforms larger models in the same family.
