Imagen de Portada

PDC & DM-SFT: A Road for LLM SQL Bug-Fix Enhancing

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Duan, Yiwen, Yu, Yonghong, Zhao, Xiaoming, Wu, Yichang, Liu, Wenbo
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
por: Limozin, Alexis, et al.
Publicado: (2026)

Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead
por: Kang, Feiyang, et al.
Publicado: (2025)

Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation
por: Zhao, Anhao, et al.
Publicado: (2026)

DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections
por: Shin, Haebin, et al.
Publicado: (2025)

Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives
por: Wang, Zecheng, et al.
Publicado: (2026)

Improving LLM Safety and Helpfulness using SFT and DPO: A Study on OPT-350M
por: Pant, Piyush
Publicado: (2025)

Dense SAE Latents Are Features, Not Bugs
por: Sun, Xiaoqing, et al.
Publicado: (2025)

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections
por: Wang, Bo, et al.
Publicado: (2025)

RLHF in an SFT Way: From Optimal Solution to Reward-Weighted Alignment
por: Du, Yuhao, et al.
Publicado: (2025)

Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning
por: Hong, Joey, et al.
Publicado: (2024)

Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them
por: Rajani, Neel, et al.
Publicado: (2025)

Continual SFT Matches Multimodal RLHF with Negative Supervision
por: Zhu, Ke, et al.
Publicado: (2024)

BiomedSQL: Text-to-SQL for Scientific Reasoning on Biomedical Knowledge Bases
por: Koretsky, Mathew J., et al.
Publicado: (2025)

AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy
por: Liu, Zihan, et al.
Publicado: (2025)

BookSQL: A Large Scale Text-to-SQL Dataset for Accounting Domain
por: Kumar, Rahul, et al.
Publicado: (2024)

Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT?
por: Nunez, Jeanmely Rojas, et al.
Publicado: (2026)

Climbing the Ladder of Reasoning: What LLMs Can-and Still Can't-Solve after SFT?
por: Sun, Yiyou, et al.
Publicado: (2025)

CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL
por: Pourreza, Mohammadreza, et al.
Publicado: (2024)

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

Evaluating NL2SQL via SQL2NL
por: Safarzadeh, Mohammadtaher, et al.
Publicado: (2025)

Fantastic Bugs and Where to Find Them in AI Benchmarks
por: Truong, Sang, et al.
Publicado: (2025)

Calibrating LLMs for Text-to-SQL Parsing by Leveraging Sub-clause Frequencies
por: Liu, Terrance, et al.
Publicado: (2025)

Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling
por: Zheng, Hang, et al.
Publicado: (2025)

Reasoning Is Not Free: Robust Adaptive Cost-Efficient Routing for LLM-as-a-Judge
por: Zhang, Wenbo, et al.
Publicado: (2026)

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
por: Xi, Zhiheng, et al.
Publicado: (2024)

Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
por: Fu, Yuqian, et al.
Publicado: (2026)

Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learning
por: Liu, Qihao, et al.
Publicado: (2025)

Knowledge Base Construction for Knowledge-Augmented Text-to-SQL
por: Baek, Jinheon, et al.
Publicado: (2025)

Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
por: Zhang, Xichen, et al.
Publicado: (2025)

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

LLM-Enhanced Data Management
por: Zhou, Xuanhe, et al.
Publicado: (2024)

SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging
por: Pourreza, Mohammadreza, et al.
Publicado: (2024)

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

Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO
por: Zeng, Zhiyuan, et al.
Publicado: (2026)

H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs
por: Tekin, Selim Furkan, et al.
Publicado: (2024)

RASL: Retrieval Augmented Schema Linking for Massive Database Text-to-SQL
por: Eben, Jeffrey, et al.
Publicado: (2025)

Confucius3-Math: A Lightweight High-Performance Reasoning LLM for Chinese K-12 Mathematics Learning
por: Wu, Lixin, et al.
Publicado: (2025)

Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL
por: Pourreza, Mohammadreza, et al.
Publicado: (2025)

First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training
por: Wei, Lai, et al.
Publicado: (2025)

User-LLM: Efficient LLM Contextualization with User Embeddings
por: Ning, Lin, et al.
Publicado: (2024)