Overconfidence is Key: Verbalized Uncertainty Evaluation in Large Language and Vision-Language Models

被引：0
|
作者：
Groot, Tobias [1 ]
Valdenegro-Toro, Matias [1 ]
机构：
[1] Department of Artificial Intelligence, University of Groningen, Netherlands
来源：
arXiv |
关键词：
Computational linguistics - Statistical tests - Uncertainty analysis;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
引用
收藏
相关论文
共 50 条
  • [31] Exploring Vision-Language Models for Imbalanced Learning
    Wang Y.
    Yu Z.
    Wang J.
    Heng Q.
    Chen H.
    Ye W.
    Xie R.
    Xie X.
    Zhang S.
    International Journal of Computer Vision, 2024, 132 (01) : 224 - 237
  • [32] Adversarial Prompt Tuning for Vision-Language Models
    Zhang, Jiaming
    Ma, Xingjun
    Wang, Xin
    Qiu, Lingyu
    Wang, Jiaqi
    Jiang, Yu-Gang
    Sang, Jitao
    COMPUTER VISION - ECCV 2024, PT XLV, 2025, 15103 : 56 - 72
  • [33] Task Bias in Contrastive Vision-Language Models
    Menon, Sachit
    Chandratreya, Ishaan Preetam
    Vondrick, Carl
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2024, 132 (06) : 2026 - 2040
  • [34] Task Residual for Tuning Vision-Language Models
    Yu, Tao
    Lu, Zhihe
    Jin, Xin
    Chen, Zhibo
    Wang, Xinchao
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 10899 - 10909
  • [35] Perceptual Grouping in Contrastive Vision-Language Models
    Ranasinghe, Kanchana
    McKinzie, Brandon
    Ravi, Sachin
    Yang, Yinfei
    Toshev, Alexander
    Shlens, Jonathon
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, 2023, : 5548 - 5561
  • [36] Adventures of Trustworthy Vision-Language Models: A Survey
    Vatsa, Mayank
    Jain, Anubhooti
    Singh, Richa
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 20, 2024, : 22650 - 22658
  • [37] Equivariant Similarity for Vision-Language Foundation Models
    Wang, Tan
    Lin, Kevin
    Li, Linjie
    Lin, Chung-Ching
    Yang, Zhengyuan
    Zhang, Hanwang
    Liu, Zicheng
    Wang, Lijuan
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 11964 - 11974
  • [38] Are Large Language Models More Honest in Their Probabilistic or Verbalized Confidence?
    Ni, Shiyu
    Bi, Keping
    Yu, Lulu
    Guo, Jiafeng
    INFORMATION RETRIEVAL, CCIR 2024, 2025, 15418 : 124 - 135
  • [39] Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks
    Zhang, Xinsong
    Zeng, Yan
    Zhang, Jipeng
    Li, Hang
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS - EMNLP 2023, 2023, : 551 - 568
  • [40] Towards Better Vision-Inspired Vision-Language Models
    Cao, Yun-Hao
    Ji, Kaixiang
    Huang, Ziyuan
    Zheng, Chuanyang
    Liu, Jiajia
    Wang, Jian
    Chen, Jingdong
    Yang, Ming
    2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2024, : 13537 - 13547
12345