← Search

Yuxuan Qiao

2 accepted papers

2024

MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark

ACL 2024findings

Recent advancements in large language models (LLMs) have showcased significant improvements in mathematics. However, traditional math benchmarks like GSM8k offer a unidimensional perspective, which fall short in providing a holistic assessment of the LLMs’ math capabilities. To address this gap, we…

2024

Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs

NeurIPS 2024poster

Vision Language Models (VLMs) demonstrate remarkable proficiency in addressing a wide array of visual questions, which requires strong perception and reasoning faculties. Assessing these two competencies independently is crucial for model refinement, despite the inherent difficulty due to the intert…