Cover Image

LLM NL2SQL Robustness: Surface Noise vs. Linguistic Variation in Traditional and Agentic Settings

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tu, Lifu, Wang, Rongguang, Sheng, Tao, Ravi, Sujjith, Roth, Dan
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Evaluating NL2SQL via SQL2NL
by: Safarzadeh, Mohammadtaher, et al.
Published: (2025)

OraPlan-SQL: A Planning-Centric Framework for Complex Bilingual NL2SQL Reasoning
by: Liu, Marianne Menglin, et al.
Published: (2025)

SPENCE: A Syntactic Probe for Detecting Contamination in NL2SQL Benchmarks
by: Safarzadeh, Mohammadtaher, et al.
Published: (2026)

Blar-SQL: Faster, Stronger, Smaller NL2SQL
by: Domínguez, José Manuel, et al.
Published: (2024)

NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions
by: Hou, Shizheng, et al.
Published: (2026)

VeriMinder: Mitigating Analytical Vulnerabilities in NL2SQL
by: Mohole, Shubham, et al.
Published: (2025)

Distill-C: Enhanced NL2SQL via Distilled Customization with LLMs
by: Hoang, Cong Duy Vu, et al.
Published: (2025)

Agentic NL2SQL to Reduce Computational Costs
by: Jehle, Dominik, et al.
Published: (2025)

RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL System
by: Chen, Zui, et al.
Published: (2025)

Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models
by: Pei, Wenqi, et al.
Published: (2025)

Can LLMs Narrate Tabular Data? An Evaluation Framework for Natural Language Representations of Text-to-SQL System Outputs
by: Singh, Jyotika, et al.
Published: (2025)

Hybrid-NL2SVA: Integrating RAG and Finetuning for LLM-based NL2SVA
by: Xiao, Weihua, et al.
Published: (2025)

H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables
by: Abhyankar, Nikhil, et al.
Published: (2024)

SQLong: Enhanced NL2SQL for Longer Contexts with LLMs
by: Nguyen, Dai Quoc, et al.
Published: (2025)

CORE-T: COherent REtrieval of Tables for Text-to-SQL
by: Soliman, Hassan, et al.
Published: (2026)

Beyond Text-to-SQL: An Agentic LLM System for Governed Enterprise Analytics APIs
by: Singh, Gundeep, et al.
Published: (2026)

SAKE: Structured Agentic Knowledge Extrapolation for Complex LLM Reasoning via Reinforcement Learning
by: He, Jiashu, et al.
Published: (2025)

PAR$^2$-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering
by: Li, Xingyu, et al.
Published: (2026)

Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System
by: Zhang, Xiang, et al.
Published: (2026)

Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets
by: Gupta, Vatsal, et al.
Published: (2023)

Personality Expression Across Contexts: Linguistic and Behavioral Variation in LLM Agents
by: Han, Bin, et al.
Published: (2026)

Language Family Matters: Evaluating LLM-Based ASR Across Linguistic Boundaries
by: Zhang, Yuchen, et al.
Published: (2026)

LLMSQL: Upgrading WikiSQL for the LLM Era of Text-to-SQL
by: Pihulski, Dzmitry, et al.
Published: (2025)

Can Linguistically Related Languages Guide LLM Translation in Low-Resource Settings?
by: Ramasethu, Aishwarya, et al.
Published: (2026)

RSL-SQL: Robust Schema Linking in Text-to-SQL Generation
by: Cao, Zhenbiao, et al.
Published: (2024)

Think Twice Before You Write -- an Entropy-based Decoding Strategy to Enhance LLM Reasoning
by: He, Jiashu, et al.
Published: (2026)

From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems
by: Mohammadjafari, Ali, et al.
Published: (2024)

Solid-SQL: Enhanced Schema-linking based In-context Learning for Robust Text-to-SQL
by: Liu, Geling, et al.
Published: (2024)

Mapping Clinical Doubt: Locating Linguistic Uncertainty in LLMs
by: Sridhar, Srivarshinee, et al.
Published: (2025)

ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL
by: Qin, Yang, et al.
Published: (2024)

GSM-SEM: Benchmark and Framework for Generating Semantically Variant Augmentations
by: Singh, Jyotika, et al.
Published: (2026)

EzSQL: An SQL intermediate representation for improving SQL-to-text Generation
by: Bhardwaj, Meher, et al.
Published: (2024)

Weaver: Interweaving SQL and LLM for Table Reasoning
by: Khoja, Rohit, et al.
Published: (2025)

Aligning Large Language Models to a Domain-specific Graph Database for NL2GQL
by: Liang, Yuanyuan, et al.
Published: (2024)

Linguistically Conditioned Semantic Textual Similarity
by: Tu, Jingxuan, et al.
Published: (2024)

Debate as Optimization: Adaptive Conformal Prediction and Diverse Retrieval for Event Extraction
by: Wang, Sijia, et al.
Published: (2024)

Targeted Augmentation for Low-Resource Event Extraction
by: Wang, Sijia, et al.
Published: (2024)

Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQL
by: Chung, Yeounoh, et al.
Published: (2025)

Splits! Flexible Sociocultural Linguistic Investigation at Scale
by: Caplan, Eylon, et al.
Published: (2025)

ROSE: An Intent-Centered Evaluation Metric for NL2SQL
by: Pei, Wenqi, et al.
Published: (2026)