通过感知验证自训练提升视觉-语言模型的推理能力
Improving Reasoning in Vision-Language Models via Perception Verified Self-Training
AI总结：
提出感知验证自训练框架，通过解耦感知与推理的CoT模板和无监督评估方法PerceptEval，结合两阶段课程学习，提升视觉-语言模型在视觉推理中的准确性并减少幻觉。
摘要：
在视觉-语言模型（VLM）中实现类人推理仍然是一个长期挑战。最近的方法利用由人类标注者或专有模型生成的思维链（CoT）理由来改进推理，这成本高昂且难以扩展。自训练通过使用模型自身的输出作为监督提供了一种有前景的替代方案。然而，现有方法通常存在视觉幻觉——理由描述不存在的视觉内容，以及语言捷径——预测依赖于文本先验而非真正的视觉基础，因为理由通常仅通过答案正确性进行过滤，而未验证视觉感知。为了解决这一局限性，我们提出了一种感知验证的自训练框架，强制进行视觉基础推理。首先，我们的方法采用CoT模板（描述-推理-结论），将感知与推理解耦，从而能够独立验证视觉理解。为了弥补缺少真实描述的不足，我们提出了PerceptEval，一种无监督方法，根据描述与图像中存在的视觉和文本元素的对齐程度来评估描述质量。结合描述验证和答案正确性，我们将数据划分为三个子集：简单（正确描述和结论）、中等（正确描述但错误结论）和困难（错误描述）。基于这种划分，我们设计了一个两阶段课程学习策略。在第一阶段，模型在简单样本上进行训练；随后在第二阶段，通过一个描述引导的推理增强过程，将中等样本纳入训练，该过程基于验证过的描述重新生成推理。仅保留具有正确结论的重新生成样本。
英文摘要：
Achieving human-like reasoning in Vision-Language Models (VLMs) remains a long-standing challenge. Recent approaches leverage Chain-of-Thought (CoT) rationales generated by human annotators or proprietary models, which are costly and difficult to scale. Self-training offers a promising alternative but often suffers from visual hallucinations and language shortcuts because rationales are filtered only by answer correctness without verifying visual perception. We propose a perception-verified self-training framework that enforces visually grounded reasoning. Our method employs a CoT template (caption-reasoning-conclusion) that disentangles perception from reasoning, enabling independent verification of visual understanding. To compensate for the absence of ground-truth captions, we introduce PerceptEval, an unsupervised method that evaluates caption quality based on its alignment with visual and textual elements in the image. Using caption verification together with answer correctness, we partition the data into easy, medium, and hard subsets and design a two-stage curriculum learning strategy. Stage 1 trains on easy samples, while Stage 2 enhances medium samples by regenerating reasoning conditioned on verified captions and retaining only those with correct conclusions. This ensures training is performed exclusively on perceptually grounded reasoning, reducing hallucinations and language shortcuts. Extensive experiments across diverse domains and models demonstrate improvements of up to 16% over standard self-training baselines, showing that our framework provides a scalable and cost-effective solution for advancing multimodal reasoning without manually annotated CoT rationales.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
