LLM-Based Config Synthesis requires Disambiguation
This addresses ambiguity issues in LLM-based program synthesis for networking configurations, but it is incremental as it builds on existing LLM methods with a new module.
The paper tackles the problem of ambiguity in user intent when using LLMs for program synthesis, specifically in networking configuration tasks like route-maps and ACLs, where overlaps cause priority issues; it proposes Clarify, a system with a Disambiguator module that helps elicit user intent, and demonstrates it on a synthetic workload for incremental synthesis and verification.
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.