Can llms express their uncertainty? an empirical evaluation of confidence elicitation in llms M Xiong, Z Hu, X Lu, Y Li, J Fu, J He, B Hooi arXiv preprint arXiv:2306.13063, 2023 | 84 | 2023 |
Proximity-informed calibration for deep neural networks M Xiong, A Deng, PWW Koh, J Wu, S Li, J Xu, B Hooi Advances in Neural Information Processing Systems 36, 2024 | 6 | 2024 |
Birds of a feather trust together: Knowing when to trust a classifier via adaptive neighborhood aggregation M Xiong, S Li, W Feng, A Deng, J Zhang, B Hooi arXiv preprint arXiv:2211.16466, 2022 | 5 | 2022 |
Robust and task-aware training of deep residual networks for varying-lead ECG classification H Ren, M Xiong, B Hooi 2021 Computing in Cardiology (CinC) 48, 1-4, 2021 | 4 | 2021 |
Prompt-and-align: prompt-based social alignment for few-shot fake news detection J Wu, S Li, A Deng, M Xiong, B Hooi Proceedings of the 32nd ACM International Conference on Information and …, 2023 | 3 | 2023 |
Graphcleaner: Detecting mislabelled samples in popular graph learning benchmarks Y Li, M Xiong, B Hooi International Conference on Machine Learning, 20195-20209, 2023 | 3 | 2023 |
Probabilistic knowledge distillation of face ensembles J Xu, S Li, A Deng, M Xiong, J Wu, J Wu, S Ding, B Hooi Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023 | 2 | 2023 |
Trust, but verify: Using self-supervised probing to improve trustworthiness A Deng, S Li, M Xiong, Z Chen, B Hooi European Conference on Computer Vision, 361-377, 2022 | 2 | 2022 |
In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation S Chen, M Xiong, J Liu, Z Wu, T Xiao, S Gao, J He arXiv preprint arXiv:2403.01548, 2024 | 1 | 2024 |
Great models think alike: Improving model reliability via inter-model latent agreement A Deng, M Xiong, B Hooi arXiv preprint arXiv:2305.01481, 2023 | 1 | 2023 |