Wanlong Fang
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes the Adversarial Prompt Disentanglement (APD) framework, a novel defense that proactively identifies and neutralizes malicious components in LLM prompts, achieving over 85% reduction in harmful outputs.
The paper proposes the Adversarial Prompt Disentanglement (APD) framework, a novel defense mechanism that proactively identifies and neutralizes malicious components in LLM prompts, achieving over 85% reduction in harmful outputs.
The paper introduces Partial Information Decomposition (PID) to quantitatively separate unique, redundant, and synergistic contributions of different modalities (e.g., vision, language) in multimodal language models, revealing distinct modality-use profiles for different task types.
Papers
Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition
The paper introduces Partial Information Decomposition (PID) to quantitatively separate unique, redundant, and synergistic contributions of different modalities (e.g., vision, language) in multimodal…