2 papers
cs.CL2024
MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models Using Odyssey Math Data
Meng Fang, Xiangpeng Wan, Fei Lu +2
Large language models (LLMs) have significantly advanced natural language understanding and demonstrated strong problem-solving abilities. Despite these successes, most LLMs still…
cs.AI2024
Enhancing the Efficiency and Accuracy of Underlying Asset Reviews in Structured Finance: The Application of Multi-agent Framework
Xiangpeng Wan, Haicheng Deng, Kai Zou +1
Structured finance, which involves restructuring diverse assets into securities like MBS, ABS, and CDOs, enhances capital market efficiency but presents significant due diligence c…