4 papers
AutoHall: Automated Factuality Hallucination Dataset Generation for Large Language Models
Zouying Cao, Yifei Yang, XiaoJing Li +1
Large language models (LLMs) have gained broad applications across various domains but still struggle with hallucinations. Currently, hallucinations occur frequently in the generat…
SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering
Zouying Cao, Yifei Yang, Hai Zhao
Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions. However, recent researches reveal safety-aligned LLMs prone to rej…
Head-wise Shareable Attention for Large Language Models
Zouying Cao, Yifei Yang, Hai Zhao
Large Language Models (LLMs) suffer from huge number of parameters, which restricts their deployment on edge devices. Weight sharing is one promising solution that encourages weigh…
LaCo: Large Language Model Pruning via Layer Collapse
Yifei Yang, Zouying Cao, Hai Zhao
Large language models (LLMs) based on transformer are witnessing a notable trend of size expansion, which brings considerable costs to both model training and inference. However, e…