5 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…
A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers
Ming Hu, Chenglong Ma, Wei Li +117
Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research, yet their progress is shaped by the compl…
ROGRAG: A Robustly Optimized GraphRAG Framework
Zhefan Wang, Huanjun Kong, Jie Ying +2
Large language models (LLMs) commonly struggle with specialized or emerging topics which are rarely seen in the training corpus. Graph-based retrieval-augmented generation (GraphRA…
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…
SeedBench: A Multi-task Benchmark for Evaluating Large Language Models in Seed Science
Jie Ying, Zihong Chen, Zhefan Wang +7
Seed science is essential for modern agriculture, directly influencing crop yields and global food security. However, challenges such as interdisciplinary complexity and high costs…