6 papers
Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models
Xinyan Jiang, Lin Zhang, Jiayi Zhang +4
Activation steering offers a promising approach to controlling the behavior of Large Language Models by directly manipulating their internal activations. However, most existing met…
What Gets Activated: Uncovering Domain and Driver Experts in MoE Language Models
Guimin Hu, Meng Li, Qiwei Peng +3
Most interpretability work focuses on layer- or neuron-level mechanisms in Transformers, leaving expert-level behavior in MoE LLMs underexplored. Motivated by functional specializa…
Tracing and Mitigating Hallucinations in Multimodal LLMs via Dynamic Attention Localization
Tiancheng Yang, Lin Zhang, Jiaye Lin +3
Multimodal Large Language Models (MLLMs) achieve strong performance on tasks like image captioning and visual question answering, but remain prone to hallucinations, where generate…
Backdooring CLIP through Concept Confusion
Lijie Hu, Junchi Liao, Weimin Lyu +5
Backdoor attacks pose a serious threat to deep learning models by allowing adversaries to implant hidden behaviors that remain dormant on clean inputs but are maliciously triggered…
Debiasing Multilingual LLMs in Cross-lingual Latent Space
Qiwei Peng, Guimin Hu, Yekun Chai +1
Debiasing techniques such as SentDebias aim to reduce bias in large language models (LLMs). Previous studies have evaluated their cross-lingual transferability by directly applying…
Mitigating Behavioral Hallucination in Multimodal Large Language Models for Sequential Images
Liangliang You, Junchi Yao, Shu Yang +3
While multimodal large language models excel at various tasks, they still suffer from hallucinations, which limit their reliability and scalability for broader domain applications.…