activity
20232025
most citedTwo Sides of Miscalibration: Identifying Over and Under-Confidence Prediction for Network Calibration

2 citations · 2 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2025

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…

cs.CL2024

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…

cs.AI2023

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…

cs.AI2023

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…

cs.LG20232 cited

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-…

cs.CV2023

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…