paper-with-me

Papers Text-To-SQL

“Text-To-SQL” 태그가 달린 논문 424편 · 필터 해제

UNJOIN: Enhancing Multi-Table Text-to-SQL Generation via Schema Simplification

2025-05-23 · Poojah Ganesan, Rajat Aayush Jha, Dan Roth, Vivek Gupta

Recent advances in large language models (LLMs) have greatly improved Text-to-SQL performance for single-table queries. But, it remains challenging in multi-table databases due to complex schema and relational operations…

RetrievalText to SQLText-To-SQL

BiomedSQL: Text-to-SQL for Scientific Reasoning on Biomedical Knowledge Bases

2025-05-23 · Mathew J. Koretsky, Maya Willey, Adi Asija, Owen Bianchi 외

Biomedical researchers increasingly rely on large-scale structured databases for complex analytical tasks. However, current text-to-SQL systems often struggle to map qualitative scientific questions into executable SQL, …

Causal Inferencescientific discoveryText to SQLText-To-SQL

ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects

2025-05-22 · Jipeng Zhang, Haolin Yang, Kehao Miao, Ruiyuan Zhang 외

Recent text-to-SQL models have achieved strong performance, but their effectiveness remains largely confined to SQLite due to dataset limitations. However, real-world applications require SQL generation across multiple d…

Text to SQLText-To-SQL

LLM-Powered Agents for Navigating Venice's Historical Cadastre

2025-05-22 · Tristan Karch, Jakhongir Saydaliev, Isabella Di Lenardo, Frédéric Kaplan

Cadastral data reveal key information about the historical organization of cities but are often non-standardized due to diverse formats and human annotations, complicating large-scale analysis. We explore as a case study…

HallucinationNatural Language QueriesText to SQLText-To-SQL

Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL

2025-05-22 · Zhewei Yao, Guoheng Sun, Lukasz Borchmann, Zheyu Shen 외

Translating natural language into SQL (Test2SQL) is a longstanding challenge at the intersection of natural language understanding and structured data access. While large language models (LLMs) have significantly improve…

Natural Language UnderstandingReinforcement Learning (RL)Text to SQLText-To-SQL

Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuning

2025-05-20 · Yusuf Denizay Dönder, Derek Hommel, Andrea W Wen-Yi, David Mimno 외

LLMs are effective at code generation tasks like text-to-SQL, but is it worth the cost? Many state-of-the-art approaches use non-task-specific LLM techniques including Chain-of-Thought (CoT), self-consistency, and fine-t…

Code GenerationText to SQLText-To-SQL

JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling

2025-05-20 · Jinwang Song, Hongying Zan, Kunli Zhang, Lingling Mu 외

Text-to-SQL, which maps natural language to SQL queries, has benefited greatly from recent advances in Large Language Models (LLMs). While LLMs offer various paradigms for this task, including prompting and supervised fi…

Text to SQLText-To-SQL

CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement Learning

2025-05-19 · Lei Sheng, Shuai-Shuai Xu

Large language models (LLMs) have demonstrated strong capabilities in translating natural language questions about relational databases into SQL queries. In particular, test-time scaling techniques such as Self-Consisten…

Text to SQLText-To-SQL

ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL

2025-05-19 · Yaxun Dai, Wenxuan Xie, Xialie Zhuang, Tianyu Yang 외

In Text-to-SQL, execution feedback is essential for guiding large language models (LLMs) to reason accurately and generate reliable SQL queries. However, existing methods treat execution feedback solely as a post-hoc sig…

Text to SQLText-To-SQL

SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMs

2025-05-19 · Yu Guo, Dong Jin, Shenghao Ye, Shuangwu Chen 외

Large Language models (LLMs) have demonstrated significant potential in text-to-SQL reasoning tasks, yet a substantial performance gap persists between existing open-source models and their closed-source counterparts. In…

DiversityText to SQLText-To-SQL

Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward

2025-05-18 · Han Weng, Boyi Liu, Yuanfeng Song, Dun Zeng 외

Reinforcement learning (RL) has been widely adopted to enhance the performance of large language models (LLMs) on Text-to-SQL tasks. However, existing methods often rely on execution-based or LLM-based Bradley-Terry rewa…

GPUGraph MatchingReinforcement Learning (RL)Text to SQL+1

Ambiguity Resolution in Text-to-Structured Data Mapping

2025-05-16 · Zhibo Hu, Chen Wang, Yanfeng Shu, Hye-Young Paik 외

Ambiguity in natural language is a significant obstacle for achieving accurate text to structured data mapping through large language models (LLMs), which affects the performance of tasks such as mapping text to agentic …

Text to SQLText-To-SQL

TARGET: Benchmarking Table Retrieval for Generative Tasks

2025-05-14 · Xingyu Ji, Parker Glenn, Aditya G. Parameswaran, Madelon Hulsebos

The data landscape is rich with structured data, often of high value to organizations, driving important applications in data analysis and machine learning. Recent progress in representation learning and generative model…

BenchmarkingRepresentation LearningRetrievalRetrieval-augmented Generation+3

Reward-SQL: Boosting Text-to-SQL via Stepwise Reasoning and Process-Supervised Rewards

2025-05-07 · Yuxin Zhang, Meihao Fan, Ju Fan, Mingyang Yi 외

Recent advances in large language models (LLMs) have significantly improved performance on the Text-to-SQL task by leveraging their powerful reasoning capabilities. To enhance accuracy during the reasoning process, exter…

Text to SQLText-To-SQL

VTS-LLM: Domain-Adaptive LLM Agent for Enhancing Awareness in Vessel Traffic Services through Natural Language

2025-05-02 · Sijin Sun, Liangbin Zhao, Ming Deng, Xiuju Fu

Vessel Traffic Services (VTS) are essential for maritime safety and regulatory compliance through real-time traffic management. However, with increasing traffic complexity and the prevalence of heterogeneous, multimodal …

ManagementNatural Language QueriesNERRelational Reasoning+2

Fact-Consistency Evaluation of Text-to-SQL Generation for Business Intelligence Using Exaone 3.5

2025-04-30 · Jeho Choi

Large Language Models (LLMs) have shown promise in enabling natural language interfaces for structured data querying through text-to-SQL generation. However, their application in real-world Business Intelligence (BI) con…

Arithmetic ReasoningText to SQLText-To-SQL

When Reasoning Beats Scale: A 1.5B Reasoning Model Outranks 13B LLMs as Discriminator

2025-04-30 · Md Fahim Anjum

Large Language Models (LLM) with reasoning capabilities offer a promising path for improving candidate evaluation in planning frameworks, but their relative performance against traditional non-reasoning models remains la…

Text to SQLText-To-SQL

Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning

2025-04-23 · Josefa Lia Stoisser, Marc Boubnovski Martell, Julien Fauqueur

This work reframes the Text-to-SQL task as a pathway for teaching large language models (LLMs) to reason over and manipulate tabular data--moving beyond the traditional focus on query generation. We propose a two-stage f…

reinforcement-learningReinforcement LearningText to SQLText-To-SQL

Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo

2025-04-17 · João Loula, Benjamin LeBrun, Li Du, Ben Lipkin 외

A wide range of LM applications require generating text that conforms to syntactic or semantic constraints. Imposing such constraints can be naturally framed as probabilistic conditioning, but exact generation from the r…

Code GenerationProbabilistic ProgrammingText to SQLText-To-SQL

Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression

2025-04-10 · Hanqi Xiao, Yi-Lin Sung, Elias Stengel-Eskin, Mohit Bansal

Post-training quantization (PTQ) reduces a model's memory footprint by mapping full precision weights into low bit weights without costly retraining, but can degrade its downstream performance especially in low 2- to 3-b…

MathMMLUQuantizationText to SQL+1
← 이전 21–40 / 424 다음 →