让AI不仅猜对，还给出正确理由，提升可信度。
Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales
- 构建带结构化理由的视觉识别数据集，引导模型理解推理过程。
- 在多个任务上准确率提升最高10.1%，理由定位和分离能力分别提高7.5%与36.5%。
- 适合关注AI可解释性与安全部署的研究者和开发者。
大型预训练基础模型在某些高风险应用中已超越人类专家，但当前评估主要依赖预测准确率，忽视了准确预测背后的推理合理性。为实现安全部署，亟需确保‘双正确’：预测正确且理由正确。为此，我们提出两阶段方案：首先构建一个为视觉识别任务提供结构化理由的新数据集；其次设计一种基于理由的优化方法，引导模型在无需人工标注的前提下，分离并定位每条理由对应的视觉证据。大量实验与消融研究显示，所提模型在多种任务上的预测准确率较现有最优方法最高提升10.1%。此外，该方法显著提升理由正确性，定位精度提高7.5%，理由分离能力提升36.5%。数据集、源代码及预训练权重已公开：https://github.com/deep-real/DCP。
原文摘要 · Abstract (English)
Large pretrained foundation models demonstrate exceptional performance and, in some high-stakes applications, even surpass human experts. However, most of these models are currently evaluated primarily on prediction accuracy, overlooking the validity of the rationales behind their accurate predictions. For the safe deployment of foundation models, there is a pressing need to ensure double-correct predictions, i.e., correct prediction backed by correct rationales. To achieve this, we propose a two-phase scheme: First, we curate a new dataset that offers structured rationales for visual recognition tasks. Second, we propose a rationale-informed optimization method to guide the model in disentangling and localizing visual evidence for each rationale, without requiring manual annotations. Extensive experiments and ablation studies demonstrate that our model outperforms state-of-the-art models by up to 10.1% in prediction accuracy across a wide range of tasks. Furthermore, our method significantly improves the model's rationale correctness, improving localization by 7.5% and disentanglement by 36.5%. Our dataset, source code, and pretrained weights: https://github.com/deep-real/DCP
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。