LLM生成网络配置时因意图模糊出错，新系统通过交互澄清提升准确性。
LLM-Based Config Synthesis requires Disambiguation
- 引入消歧模块，让LLM通过用户交互明确配置意图。
- 实测显示大型云环境中有上百处规则重叠导致优先级混乱。
- 适用于需精确理解更新意图的自动化配置场景。
使用大语言模型（LLM）进行程序合成时，除幻觉外，用户意图模糊也是关键问题。本文以网络路由策略和访问控制列表（ACLs）的增量配置合成为例，揭示了由于头部空间频繁重叠，导致规则优先级无法由LLM推断，必须依赖用户交互。在大型云环境中测量发现，复杂ACL存在数百个重叠项，证明模糊性真实存在。为此，我们提出原型系统Clarify，其通过新增的消歧模块（Disambiguator）辅助LLM获取用户意图。在小规模合成工作负载上，Clarify在完成消歧后逐步生成路由策略，并进行验证。该方法在目标意图可被正确合成但整合方式存在歧义、可能引发不同全局行为的场景中具有普遍适用价值。
原文摘要 · Abstract (English)
Beyond hallucinations, another problem in program synthesis using LLMs is ambiguity in user intent. We illustrate the ambiguity problem in a networking context for LLM-based incremental configuration synthesis of route-maps and ACLs. These structures frequently overlap in header space, making the relative priority of actions impossible for the LLM to infer without user interaction. Measurements in a large cloud identify complex ACLs with 100's of overlaps, showing ambiguity is a real problem. We propose a prototype system, Clarify, which uses an LLM augmented with a new module called a Disambiguator that helps elicit user intent. On a small synthetic workload, Clarify incrementally synthesizes routing policies after disambiguation and then verifies them. Our treatment of ambiguities is useful more generally when the intent of updates can be correctly synthesized by LLMs, but their integration is ambiguous and can lead to different global behaviors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。