arXiv cs.AI· Liang Zhang, Beno\^{i}t Daireaux, Sergey Alyaev·· 15 小时前AI 评分22
别急着怪 LLM，先诊断工作流：本体落地 NL-to-DSL 语义解析的角色级难度画像
Before Blaming the LLM, Diagnose the Workflow: A Role-Level Difficulty Profile for Translating Natural Language into Ontology-Grounded Statements
AI 导读
针对本体落地的 ABox DSL 生成任务，论文提出一套角色级难度画像，把诊断变量分配到 Input、Generator、Output、Validator、Repairer 五个工作流角色上，共含输入充分性、上下文可得性、落地复杂度、模板匹配度、词汇覆盖率、验证强度、错误可观测性七项变量。
正文 · 原文
Abstract:Natural-language-to-domain-specific-language (NL-to-DSL) semantic parsing systems increasingly translate informal user descriptions into structured artifacts such as Structured Query Language (SQL) queries, Application Programming Interface (API) calls, workflows, formal specifications, and ontology-grounded domain-specific language (DSL) statements. This paper focuses on ontology-grounded Assertion Box (ABox) DSL generation: the translation of natural language domain descriptions into assertion-level DSL statements grounded in a pre-existing ontology vocabulary. In this setting, syntactic validity is often easier to achieve than semantic adequacy. Failures are frequently attributed to weak generator models, but recurring sources of difficulty are also structural: insufficient input, weak domain grounding, output template and vocabulary gaps, weak validation, and non-local repair.
We propose a role-level difficulty profile for diagnosing difficulty in ontology-grounded NL-to-DSL semantic parsing at the workflow level. The profile organizes diagnostic variables across five recurring workflow roles: Input, Generator, Output, Validator, and Repairer. The seven variables are input sufficiency, context availability, grounding complexity, template fit, vocabulary coverage, validation strength, and error observability. Practitioners construct the difficulty profile through qualitative judgment over available evidence. This experience-informed, non-exhaustive difficulty profile is intended to support workflow diagnosis and guide redesign or human-in-the-loop intervention.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.35267 [cs.AI] |
| (or arXiv:2610.35267v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35267 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Liang Zhang [view email]
[v1]
Mon, 26 Oct 2026 11:44:21 UTC (48 KB)
来源：arXiv cs.AI · arxiv.org