Haitian Zhong — accepted AI-conference papers

2025

REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing

Haitian Zhong, Yuhuan Liu, Ziyang Xu, Guofan Liu, Qiang Liu, Shu Wu +3

EMNLP 2025

Large language model editing methods frequently suffer from overfitting, wherein factual updates can propagate beyond their intended scope, overemphasizing the edited target even when it’s contextually inappropriate. To address this challenge, we introduce REACT (Representation Extraction And Contro

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark

Han Huang, Haitian Zhong, Tao Yu, Qiang Liu, Shu Wu, Liang Wang +1

NeurIPS 2024poster

Recently, knowledge editing on large language models (LLMs) has received considerable attention. Compared to this, editing Large Vision-Language Models (LVLMs) faces extra challenges from diverse data modalities and complicated model components, and data for LVLMs editing are limited. The existing L…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗