AI 中文总结
本研究通过对照实验评估LLMs在语法工程中的作用，发现GPT-5.4优于gpt-oss-120b，LLMs可支持语法开发中间阶段但需人类专业知识，还贡献了新粤语符号语法资源。
AI 中文摘要
本文介绍了新的粤语ParGram资源，并在对照实验范式中评估了LLMs在知识驱动型语法工程中的应用。以粤语ParGram资源为黄金标准，搭配对应的英文基线，我们研究OpenAI的gpt-oss-120b和GPT-5.4能否在系统变化的提示条件下，从句子和目标形式结构中生成机器可处理的语法。GPT-5.4的表现优于gpt-oss-120b，而从目标形式结构生成的语法通常优于从句子生成的语法。尽管两种模型都能生成本地合理的短语结构规则、词法条目和模板，但它们常常难以协调相互作用的形式约束，尤其是在多结构设置中。这些结果明确了当前LLMs的能力与局限性，可潜在整合到AI辅助的专家工作流程中：LLMs可支持语法开发的中间阶段，但人类语言专业知识对分析、验证和优化仍至关重要。该研究还贡献了新的粤语符号语法资源。
英文摘要
This paper presents new Cantonese ParGram resources and evaluates LLMs for knowledge-driven grammar engineering within a controlled experimental paradigm. Using Cantonese ParGram resources as gold standards, with corresponding English baselines, we investigate whether OpenAI's gpt-oss-120b and GPT-5.4 can generate machine-processable grammars from sentences and target formal structures under systematically varied prompting conditions. GPT-5.4 outperformed gpt-oss-120b, while grammars generated from target formal structures generally outperformed those generated from sentences. Although both models could generate locally plausible phrase-structure rules, lexical entries, and templates, they often struggled to coordinate interacting formal constraints, especially in multi-construction settings. The results characterize both the capabilities and limitations of current LLMs for potential integration into AI-assisted expert workflows: LLMs may support intermediate stages of grammar development, but human linguistic expertise remains central to analysis, validation, and refinement. The study also contributes new Cantonese symbolic grammatical resources.
CommentsAccepted to Findings of the Association for Computational Linguistics: EMNLP 2026
