LLM-Based Config Synthesis requires Disambiguation

TL;DR

This paper addresses ambiguity in LLM-based program synthesis, especially in networking configurations, proposing a system called Clarify with a Disambiguator to improve intent understanding and synthesis accuracy.

Contribution

Introduces Clarify, a system with a Disambiguator module that reduces ambiguity in LLM-based configuration synthesis through user interaction.

Findings

Clarify effectively disambiguates user intent in network configurations.

The system synthesizes and verifies routing policies after disambiguation.

Ambiguity significantly impacts LLM-based synthesis accuracy in complex scenarios.

Abstract

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.