13 papers
OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents
Jiahao Ying, Boxian Ai, Wei Tang +2
Skills, i.e., structured workflow instructions distilled for large language models (LLMs), are becoming an increasingly important mechanism for improving agent performance on real-…
UniPPTBench: A Unified Benchmark for Presentation Generation Across Diverse Input Settings
Bo Zhao, Maosheng Pang, Chen Zhang +3
Existing works typically focus on presentation generation under isolated input settings, whereas real-world use cases span diverse scenarios, including vague user prompts, long doc…
Beyond Benchmarks: Understanding Mixture-of-Experts Models through Internal Mechanisms
Jiahao Ying, Mingbao Lin, Qianru Sun +1
Mixture-of-Experts (MoE) architectures have emerged as a promising direction, offering efficiency and scalability by activating only a subset of parameters during inference. Howeve…
EffiEval: Efficient and Generalizable Model Evaluation via Capability Coverage Maximization
Yaoning Wang, Jiahao Ying, Yixin Cao +2
The rapid advancement of large language models (LLMs) and the development of increasingly large and diverse evaluation benchmarks have introduced substantial computational challeng…
Disentangling Language and Culture for Evaluating Multilingual Large Language Models
Jiahao Ying, Wei Tang, Yiran Zhao +3
This paper introduces a Dual Evaluation Framework to comprehensively assess the multilingual capabilities of LLMs. By decomposing the evaluation along the dimensions of linguistic…
Model Utility Law: Evaluating LLMs beyond Performance through Mechanism Interpretable Metric
Yixin Cao, Jiahao Ying, Yaoning Wang +3
Large Language Models (LLMs) have become indispensable across academia, industry, and daily applications, yet current evaluation methods struggle to keep pace with their rapid deve…