Lvyuan Han — accepted AI-conference papers

2026

Lost in Benchmarks? Rethinking Large Language Model Benchmarking with Item Response Theory

Hongli Zhou, Hui Huang, Ziqing Zhao, Lvyuan Han, Huicheng Wang, Kehai Chen +7

AAAI 2026technical

The evaluation of large language models (LLMs) via benchmarks is widespread, yet inconsistencies between different leaderboards and poor separability among top models raise concerns about their ability to accurately reflect authentic model capabilities. This paper provides a critical analysis of ben

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

RM-Distiller: Exploiting Generative LLM for Reward Model Distillation

Hongli Zhou, Hui Huang, Wei Liu, Chenglong Wang, Xingyuan Bu, Lvyuan Han +5

IJCAI 2026

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. Due to the difficulty of obtaining high-quality human preference annotations, distilling preferences from generative LLMs has emerged as a standard practice. However, existing approaches predomin

Cited by 0 Scholar ↗