2 citations · 2 across the 6 of their papers we have counts for
6 papers
Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
Shuang Ao, Yi Dong, Jinwei Hu +1
Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) enhances adaptability while reducing computational costs. However, fine-tuning can compromise safety alignm…
CSS: Contrastive Semantic Similarity for Uncertainty Quantification of LLMs
Shuang Ao, Stefan Rueger, Advaith Siddharthan
Despite the impressive capability of large language models (LLMs), knowing when to trust their generations remains an open challenge. The recent literature on uncertainty quantific…
Empirical Optimal Risk to Quantify Model Trustworthiness for Failure Detection
Shuang Ao, Stefan Rueger, Advaith Siddharthan
Failure detection (FD) in AI systems is a crucial safeguard for the deployment for safety-critical tasks. The common evaluation method of FD performance is the Risk-coverage (RC) c…
Building Safe and Reliable AI systems for Safety Critical Tasks with Vision-Language Processing
Shuang Ao
Although AI systems have been applied in various fields and achieved impressive performance, their safety and reliability are still a big concern. This is especially important for…
Two Sides of Miscalibration: Identifying Over and Under-Confidence Prediction for Network Calibration
Shuang Ao, Stefan Rueger, Advaith Siddharthan
Proper confidence calibration of deep neural networks is essential for reliable predictions in safety-critical tasks. Miscalibration can lead to model over-confidence and/or under-…
Confidence-Aware Calibration and Scoring Functions for Curriculum Learning
Shuang Ao, Stefan Rueger, Advaith Siddharthan
Despite the great success of state-of-the-art deep neural networks, several studies have reported models to be over-confident in predictions, indicating miscalibration. Label Smoot…