4 papers
PromptCD: Test-Time Behavior Enhancement via Polarity-Prompt Contrastive Decoding
Baolong Bi, Yuyao Ge, Shenghua Liu +9
Reliable AI systems require large language models (LLMs) to exhibit behaviors aligned with human preferences and values. However, most existing alignment approaches operate at trai…
CorrDetail: Visual Detail Enhanced Self-Correction for Face Forgery Detection
Binjia Zhou, Hengrui Lou, Lizhe Chen +6
With the swift progression of image generation technology, the widespread emergence of facial deepfakes poses significant challenges to the field of security, thus amplifying the u…
PIS: Linking Importance Sampling and Attention Mechanisms for Efficient Prompt Compression
Lizhe Chen, Binjia Zhou, Yuyao Ge +2
Large language models (LLMs) have achieved remarkable progress, demonstrating unprecedented capabilities across various natural language processing tasks. However, the high costs a…
Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking
Yuyao Ge, Shenghua Liu, Yiwei Wang +4
Recent advances in Large Language Models (LLMs) have introduced Reasoning Large Language Models (RLLMs), which employ extended thinking processes with reflection and self-correctio…