Structure-Aware NL-to-SQL for SFC Provisioning via AST-Masking Empowered Language Models

TL;DR

This paper introduces AST-Masking, a structure-aware fine-tuning method for language models that significantly improves the accuracy and syntactic correctness of NL-to-SQL translation in SFC provisioning.

Contribution

The paper proposes AST-Masking, a novel syntax-aware fine-tuning approach using SQL ASTs to enhance NL-to-SQL translation without increasing inference complexity.

Findings

FLAN-T5 achieves 99.6% execution accuracy.

Gemma's accuracy improves from 7.5% to 72.0%.

AST-Masking outperforms conventional fine-tuning methods.

Abstract

Effective Service Function Chain (SFC) provisioning requires precise orchestration in dynamic and latency-sensitive networks. Reinforcement Learning (RL) improves adaptability but often ignores structured domain knowledge, which limits generalization and interpretability. Large Language Models (LLMs) address this gap by translating natural language (NL) specifications into executable Structured Query Language (SQL) commands for specification-driven SFC management. Conventional fine-tuning, however, can cause syntactic inconsistencies and produce inefficient queries. To overcome this, we introduce Abstract Syntax Tree (AST)-Masking, a structure-aware fine-tuning method that uses SQL ASTs to assign weights to key components and enforce syntax-aware learning without adding inference overhead. Experiments show that AST-Masking significantly improves SQL generation accuracy across multiple language models. FLAN-T5 reaches an Execution Accuracy (EA) of 99.6%, while Gemma achieves the largest absolute gain from 7.5% to 72.0%. These results confirm the effectiveness of structure-aware fine-tuning in ensuring syntactically correct and efficient SQL generation for interpretable SFC orchestration.