5 papers
Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning
Yiming Huang, Zhenbo Shi, Shuzheng Gao +3
Reinforcement Learning with Verifiable Rewards (RLVR) is an essential paradigm that enhances the reasoning capabilities of Large Language Models (LLMs). However, existing methods t…
Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs
Yiming Huang, Zhenbo Shi, Xin-Cheng Wen +4
Unsupervised reinforcement learning (RL) has emerged as a promising paradigm for enabling self-improvement in large language models (LLMs). However, existing unsupervised RL-based…
TCSR-SQL: Towards Table Content-aware Text-to-SQL with Self-retrieval
Wenbo Xu, Liang Yan, Chuanyi Liu +5
Large Language Model-based (LLM-based) Text-to-SQL methods have achieved important progress in generating SQL queries for real-world applications. When confronted with table conten…
Data Dependency-Aware Code Generation from Enhanced UML Sequence Diagrams
Wenxin Mao, Zhitao Wang, Long Wang +7
Large language models (LLMs) excel at generating code from natural language (NL) descriptions. However, the plain textual descriptions are inherently ambiguous and often fail to ca…
Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunities
Yiming Huang, Jiyu Guo, Wenxin Mao +4
Converting natural language (NL) questions into SQL queries, referred to as Text-to-SQL, has emerged as a pivotal technology for facilitating access to relational databases, especi…