arXiv cs.AI· Shashank·· 4 小时前AI 评分38
FCP:用于验证 LLM 生成产物的形式化上下文协议
FCP: Formal Context Protocol for Verifying LLM-Generated Artifacts
AI 导读
研究者提出形式化上下文协议 FCP,将 AI 生成产物直接对照需求本身进行验证,把一致性判定交给模型检查器和 SMT 求解器,把保真度问题转化为可被具体反例反驳的检查。
正文 · 原文
Abstract:When a language model writes both an artifact and the tests meant to check it, a passing test is weak evidence: one misreading of the request yields a faulty artifact and a check that accepts it. We present the Formal Context Protocol (FCP), which checks AI-generated artifacts against the request itself. FCP separates conformance (does the artifact satisfy a formal reading of a requirement?), which model checkers and SMT solvers decide, from fidelity (does the reading mean what the prose means?), which has no decision procedure but is refutable by a concrete witness. Eight ways a proof can falsely certify a requirement each become a mechanical check that returns a witness, and what no machine can settle becomes concrete questions for the request's author. Adapters place hardware, text, agents and code on the same engines. On four hardware designs, trusting AI-written assertions certified 23% of violated requirements, and FCP certified none. On ten code tasks, code from three language models passed its own tests and violated the request every time. Trusting the tests certified all 33 violations, and FCP certified three. Agreement among models, readings or tests did not imply correctness.
| Comments: | 5 figures, 13 tables. Code and data: this https URL |
| Subjects: | Hardware Architecture (cs.AR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.21679 [cs.AR] |
| (or arXiv:2611.21679v1 [cs.AR] for this version) | |
| https://doi.org/10.48550/arXiv.2611.21679 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shashank Chaurasia [view email]
[v1]
Sun, 15 Nov 2026 03:06:34 UTC (45 KB)
来源:arXiv cs.AI · arxiv.org