Saved in:
Bibliographic Details
Main Authors: Tu, Lifu, Wang, Rongguang, Sheng, Tao, Ravi, Sujjith, Roth, Dan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.17017
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914404498407424
author Tu, Lifu
Wang, Rongguang
Sheng, Tao
Ravi, Sujjith
Roth, Dan
author_facet Tu, Lifu
Wang, Rongguang
Sheng, Tao
Ravi, Sujjith
Roth, Dan
contents Robustness evaluation for Natural Language to SQL (NL2SQL) systems is essential because real-world database environments are dynamic, noisy, and continuously evolving, whereas conventional benchmark evaluations typically assume static schemas and well-formed user inputs. In this work, we introduce a robustness evaluation benchmark containing approximately ten types of perturbations and conduct evaluations under both traditional and agentic settings. We assess multiple state-of-the-art large language models (LLMs), including Grok-4.1, Gemini-3-Pro, Claude-Opus-4.6, and GPT-5.2. Our results show that these models generally maintain strong performance under several perturbations; however, notable performance degradation is observed for surface-level noise (e.g., character-level corruption) and linguistic variation that preserves semantics while altering lexical or syntactic forms. Furthermore, we observe that surface-level noise causes larger performance drops in traditional pipelines, whereas linguistic variation presents greater challenges in agentic settings. These findings highlight the remaining challenges in achieving robust NL2SQL systems, particularly in handling linguistic variability.
format Preprint
id arxiv_https___arxiv_org_abs_2603_17017
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LLM NL2SQL Robustness: Surface Noise vs. Linguistic Variation in Traditional and Agentic Settings
Tu, Lifu
Wang, Rongguang
Sheng, Tao
Ravi, Sujjith
Roth, Dan
Computation and Language
Artificial Intelligence
Robustness evaluation for Natural Language to SQL (NL2SQL) systems is essential because real-world database environments are dynamic, noisy, and continuously evolving, whereas conventional benchmark evaluations typically assume static schemas and well-formed user inputs. In this work, we introduce a robustness evaluation benchmark containing approximately ten types of perturbations and conduct evaluations under both traditional and agentic settings. We assess multiple state-of-the-art large language models (LLMs), including Grok-4.1, Gemini-3-Pro, Claude-Opus-4.6, and GPT-5.2. Our results show that these models generally maintain strong performance under several perturbations; however, notable performance degradation is observed for surface-level noise (e.g., character-level corruption) and linguistic variation that preserves semantics while altering lexical or syntactic forms. Furthermore, we observe that surface-level noise causes larger performance drops in traditional pipelines, whereas linguistic variation presents greater challenges in agentic settings. These findings highlight the remaining challenges in achieving robust NL2SQL systems, particularly in handling linguistic variability.
title LLM NL2SQL Robustness: Surface Noise vs. Linguistic Variation in Traditional and Agentic Settings
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2603.17017