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

2026-01-24

AI Summary

Existing natural language to SQL (NL-to-SQL) approaches often neglect structured domain knowledge in service function chaining (SFC) orchestration, leading to syntactic errors, poor generalization, and limited interpretability. To address this, this work proposes an AST-Masking mechanism that incorporates structural awareness during the fine-tuning of large language models—such as FLAN-T5 and Gemma—by weighting critical components derived from SQL abstract syntax trees. This approach seamlessly integrates syntactic constraints into training without introducing additional inference overhead. Empirical results demonstrate substantial improvements in generation quality: FLAN-T5 achieves a 99.6% execution accuracy, while Gemma’s performance surges from 7.5% to 72.0%. These findings validate the effectiveness of the proposed method in generating efficient, correct, and interpretable SQL queries tailored to SFC scenarios.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

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.

Problem

• NL-to-SQL
• Service Function Chain
• Structured Query Language
• Natural Language Specification
• SFC Provisioning

Innovation

• AST-Masking
• Structure-Aware NL-to-SQL
• Service Function Chain (SFC)
• Abstract Syntax Tree (AST)
• Syntax-Aware Fine-Tuning