从幻觉到意图：用于视觉-语言推理的视觉理由学习
From Illusion to Intention: Visual Rationale Learning for Vision-Language Reasoning
AI总结：
本文提出视觉理由学习（ViRL），通过将视觉动作作为核心推理元素，提升视觉-语言推理模型的透明度和可信度。
摘要：
近年来，视觉-语言推理领域的发展突显了图像推理的重要性，其中模型会主动将推理过程扎根于视觉证据。然而，现有框架将视觉动作视为可选工具，虽然提升了指标，但使推理过程未被扎根，作物效果不佳。这一差距导致了图像推理的幻觉现象：模型似乎具有视觉基础，但依赖于上下文无关的动作，这些动作既不细化感知也不引导推理走向正确答案。我们通过重新将视觉动作视为核心推理原始元素而非可选工具来解决这一问题，我们称之为视觉理由学习（visual rationalization），即文本链式思维的视觉类比。基于这一洞察，我们提出了视觉理由学习（ViRL），一种端到端的范式，其训练扎根于视觉理由本身。ViRL整合（1）过程监督与真实理由，（2）通过步骤级奖励塑造实现目标对齐，以及（3）细粒度信用分配以区分正确、冗余和错误的动作。通过确保每个动作都对推理链有有意义的贡献，ViRL使模型能够
英文摘要：
Recent advances in vision-language reasoning underscore the importance of thinking with images, where models actively ground their reasoning in visual evidence. Yet, prevailing frameworks treat visual actions as optional tools, boosting metrics but leaving reasoning ungrounded and crops ineffective. This gap gives rise to the illusion of thinking with images: models seem visually grounded but rely on context-agnostic actions that neither refine perception nor guide reasoning toward correct answers. We address this problem by reframing visual actions as core reasoning primitives rather than optional tools, which we term visual rationalization, the visual analogue of textual Chain-of-Thought. Building on this insight, we propose Visual Rationale Learning (ViRL), an end-to-end paradigm that grounds training in the visual rationale itself. ViRL integrates (1) Process Supervision with ground-truth rationales, (2) Objective Alignment via step-level reward shaping, and (3) Fine-Grained Credit Assignment to distinguish correct, redundant, and erroneous actions. By ensuring each action contributes meaningfully to the reasoning chain, ViRL enables models to "get the right answer for the right visual reason". Trained purely with end-to-end RL, ViRL achieves state-of-the-art results across benchmarks spanning perception, hallucination, and reasoning. This work establishes visual rationalization as a task-agnostic, process-grounded paradigm for building transparent, verifiable, and trustworthy vision-language models.
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。
