Author

Shiji Zhao

h-index 10 View on Semantic Scholar

We have 3 of 28 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding

Large Vision-Language Models (LVLMs) have achieved remarkable performance across a wide range of tasks; however, they often inherit social biases from their training data, resulting in biased behavior when processing portraits from different social groups. Existing debiasing approaches typically compare token probabili...

Yisong Xiao, Aishan Liu, Yongxin Huang et al. · 0 citations

Preprint Aug 2026

A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination

This work proposes a multimodal automated red team jailbreak method named Hierarchical Atomic Combination Attack (HACA), based on a six-dimensional strategy space, where a cross-modal joint planner is used to select and combine the different atomic jailbreak strategy for subsequent jailbreak command generation.

Shiji Zhao, Yuxuan Zhou, Chen Xiong et al. · 0 citations

Preprint Aug 2026

HiRoute: Hierarchical Routed Prompt Tuning for Safety Alignment of Large Language Models

Experiments across three instruction-tuned models show that HiRoute achieves high safety rates across multiple safety benchmarks while preserving safe-response helpfulness, reducing over-refusal, and maintaining competitive performance on general-purpose tasks.

Fang-Zhou Chen, Shiji Zhao, Mengyan Wang et al. · 0 citations