Poster · Sydney

BiasTrojan: LLM Judgers Are Easily Distorted by Few Hundreds of Contrastive Biased Training Data

Name: BiasTrojan: LLM Judgers Are Easily Distorted by Few Hundreds of Contrastive Biased Training Data
Start: 2026-12-09T10:00:00+11:00
End: 2026-12-09T13:00:00+11:00
Location: Hall 1-4, ICC Sydney

When: Wed 9 Dec 2026, 10:00–13:00 AEDT
Where: Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session: Sydney Poster Session 3
Authors: Zichen TANG, Zhenheng Tang, Qian Wang, Gaoning Pan, Yuhan Yang, Wei He, Shaohuai Shi, Xiaowen Chu, Bo Li
Organisations: Hong Kong University of Science and Technology, National University of Singapore, Hangzhou Dianzi University, Shanghai Jiao Tong University, Universidad Politécnica de Madrid, Harbin Institute of Technology, Hong Kong University of Science and Technology (Guangzhou)
QRS classification: Language models

Open in schedule Official page