4 papers
HyperLens: Quantifying Cognitive Effort in LLMs with Fine-grained Confidence Trajectory
Chengda Lu, Xiaoyu Fan, Wei Xu
While Large Language Models (LLMs) achieve strong performance across diverse tasks, their inference dynamics remain poorly understood because of the limited resolution of existing…
How Would Oblivious Memory Boost Graph Analytics on Trusted Processors?
Jiping Yu, Xiaowei Zhu, Kun Chen +4
Trusted processors provide a way to perform joint computations while preserving data privacy. To overcome the performance degradation caused by data-oblivious algorithms to prevent…
Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?
Chengda Lu, Xiaoyu Fan, Yu Huang +3
Jailbreak attacks have been observed to largely fail against recent reasoning models enhanced by Chain-of-Thought (CoT) reasoning. However, the underlying mechanism remains underex…
GORAM: Graph-oriented ORAM for Efficient Ego-centric Queries on Federated Graphs
Xiaoyu Fan, Kun Chen, Jiping Yu +4
Ego-centric queries, focusing on a target vertex and its direct neighbors, are essential for various applications. Enabling such queries on graphs owned by mutually distrustful dat…