137 citations · 214 across the 22 of their papers we have counts for
4 papers · 1 filter
CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective
Jiayu Liu, Zhenya Huang, Wei Dai +7
Although large language models (LLMs) show promise in solving complex mathematical tasks, existing evaluation paradigms rely solely on a coarse measure of overall answer accuracy,…
From Objectives to Questions: A Planning-based Framework for Educational Mathematical Question Generation
Cheng Cheng, Zhenya Huang, Guanhao Zhao +5
Automatically generating high-quality mathematical problems that align with educational objectives is a crucial task in NLP-based educational technology. Traditional generation met…
am-ELO: A Stable Framework for Arena-based LLM Evaluation
Zirui Liu, Jiatong Li, Yan Zhuang +5
Arena-based evaluation is a fundamental yet significant evaluation paradigm for modern AI models, especially large language models (LLMs). Existing framework based on ELO rating sy…
MiMu: Mitigating Multiple Shortcut Learning Behavior of Transformers
Lili Zhao, Qi Liu, Wei Chen +5
Empirical Risk Minimization (ERM) models often rely on spurious correlations between features and labels during the learning process, leading to shortcut learning behavior that und…