6 papers
Every Token Leaves a Ripple in the Stream of Thought: Eliciting Model-Internal Token Saliency for Chain-of-Thought Compression
Tianyi Zhao, Yinhan He, Wendy Zheng +2
Chain-of-thought (CoT) reasoning improves multi-step problem solving, but long reasoning traces inflate inference cost. Token-level CoT compression reduces this cost by pruning ful…
Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs
Tianyi Zhao, Yinhan He, Wendy Zheng +2
Large language models are often not just wrong, but \emph{confidently wrong}: when they produce factually incorrect answers, they tend to verbalize overly high confidence rather th…
REHEARSE: Experiential Rehearsal for Verbal Confidence Calibration in Large Language Models
Ke Fang, Tianyi Zhao, Qianwen Wang +1
Large language models (LLMs) often express verbal confidence that is poorly aligned with actual correctness, limiting their reliability in safety-critical applications. Existing pr…
Conformalized Link Prediction on Graph Neural Networks
Tianyi Zhao, Jian Kang, Lu Cheng
Graph Neural Networks (GNNs) excel in diverse tasks, yet their applications in high-stakes domains are often hampered by unreliable predictions. Although numerous uncertainty quant…
A Survey on Safe Multi-Modal Learning System
Tianyi Zhao, Liangliang Zhang, Yao Ma +1
In the rapidly evolving landscape of artificial intelligence, multimodal learning systems (MMLS) have gained traction for their ability to process and integrate information from di…
Unveiling the Role of Message Passing in Dual-Privacy Preservation on GNNs
Tianyi Zhao, Hui Hu, Lu Cheng
Graph Neural Networks (GNNs) are powerful tools for learning representations on graphs, such as social networks. However, their vulnerability to privacy inference attacks restricts…