让大模型学会识别自己何时出错，提升回答可靠性
The Confidence Paradox: Can LLM Know When It's Wrong
- 用自监督方法让模型自信程度更贴近真实正确率
- 在多个数据集上准确率提升4.3%，过自信现象显著减少
- 适合关注模型可信度和伦理安全的研究者
文档视觉问答（DocVQA）模型常在不确定情况下产生过度自信或不符合伦理的回答。现有模型如LayoutLMv3、UDOP和DONUT虽注重准确性，但缺乏伦理校准能力。本文提出HonestVQA——一种模型无关的自监督框架，通过加权损失与对比学习实现模型置信度与正确性的对齐。引入新的评估指标：诚实度得分（H-Score）和伦理置信指数（ECI）。HonestVQA在SpDocVQA、InfographicsVQA和SROIE等多个数据集上，准确率与F1值最高提升4.3%，同时降低过自信现象。模型具备良好跨领域泛化能力，在测试中达到78.9%准确率与76.1% F1分数。
原文摘要 · Abstract (English)
Document Visual Question Answering (DocVQA) models often produce overconfident or ethically misaligned responses, especially under uncertainty. Existing models like LayoutLMv3, UDOP, and DONUT focus on accuracy but lack ethical calibration. We propose HonestVQA, a model-agnostic, self-supervised framework that aligns model confidence with correctness using weighted loss and contrastive learning. We introduce two new metrics Honesty Score (H-Score) and Ethical Confidence Index (ECI)-to evaluate ethical alignment. HonestVQA improves accuracy and F1 by up to 4.3% across SpDocVQA, InfographicsVQA, and SROIE datasets, while reducing overconfidence. It also generalizes well across domains, achieving 78.9% accuracy and 76.1% F1-score.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。