4 papers
The Alignment Paradox: How Post-Training Amplifies Confident Hallucinations in Language Models
Qingjia Huang, Yakai Li, Jianguo Wu +5
Large language models (LLMs) can produce factually incorrect answers with high confidence, undermining their reliability and limiting the effectiveness of uncertainty-based error d…
vCause: Efficient and Verifiable Causality Analysis for Cloud-based Endpoint Auditing
Qiyang Song, Qihang Zhou, Xiaoqi Jia +5
In cloud-based endpoint auditing, security administrators often rely on the cloud to perform causality analysis over log-derived versioned provenance graphs to investigate suspicio…
Focusing on Language: Revealing and Exploiting Language Attention Heads in Multilingual Large Language Models
Xin Liu, Qiyang Song, Qihang Zhou +5
Large language models (LLMs) increasingly support multilingual understanding and generation. Meanwhile, efforts to interpret their internal mechanisms have emerged, offering insigh…
Latent Knowledge Scalpel: Precise and Massive Knowledge Editing for Large Language Models
Xin Liu, Qiyang Song, Shaowen Xu +6
Large Language Models (LLMs) often retain inaccurate or outdated information from pre-training, leading to incorrect predictions or biased outputs during inference. While existing…