6 papers
Knowledge-to-Verification: Exploring RLVR for LLMs in Knowledge-Intensive Domains
Zhonghang Yuan, Zhefan Wang, Fang Hu +7
Reinforcement learning with verifiable rewards (RLVR) has demonstrated promising potential to enhance the reasoning capabilities of large language models (LLMs) in domains such as…
PRING: Rethinking Protein-Protein Interaction Prediction from Pairs to Graphs
Xinzhe Zheng, Hao Du, Fanding Xu +9
Deep learning-based computational methods have achieved promising results in predicting protein-protein interactions (PPIs). However, existing benchmarks predominantly focus on iso…
Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization
Jiaqi Wei, Hao Zhou, Xiang Zhang +6
Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs). However, standard RAG pipelines often fail t…
Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System
Haoyang Su, Renqi Chen, Shixiang Tang +10
The rapid advancement of scientific progress requires innovative tools that can accelerate knowledge discovery. Although recent AI methods, particularly large language models (LLMs…
GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
Zihong Chen, Wanli Jiang, Jinzhe Li +4
Fine-tuning for large language models (LLMs) typically requires substantial amounts of high-quality supervised data, which is both costly and labor-intensive to acquire. While synt…
Towards Efficient and Intelligent Laser Weeding: Method and Dataset for Weed Stem Detection
Dingning Liu, Jinzhe Li, Haoyang Su +5
Weed control is a critical challenge in modern agriculture, as weeds compete with crops for essential nutrient resources, significantly reducing crop yield and quality. Traditional…