视频大型多模态模型能否像怀疑者一样思考，还是加倍下注：关于可废止视频蕴含的研究
Can Video Large Multimodal Models Think Like Doubters-or Double-Down: A Study on Defeasible Video Entailment
AI总结：
本研究提出可废止视频蕴含（DVidE）任务，通过反事实思维链框架和ASR+LLM生成框架，增强视频大型多模态模型的动态推理能力，并构建基准数据集验证有效性。
摘要：
视频大型多模态模型（VLMMs）在理解视频内容方面取得了显著进展，但它们常常在抽象和自适应推理方面遇到困难，即当新信息出现时能够修正其解释的能力。在现实中，结论很少是一成不变的；额外的上下文可以加强或削弱最初的推断。为了解决这个问题，我们引入了可废止视频蕴含（DVidE），这是一个新任务，挑战模型像怀疑者一样思考，根据不断演变的证据不断更新其推理。在DVidE中，给定一个视频前提和一个文本假设，模型必须确定新的更新是加强还是削弱了该假设（分类版本），或者生成一个连贯的更新来修改蕴含关系（生成版本）。为了解决分类任务，我们提出了反事实思维链框架，利用反事实推理、ASR增强的视频内容和理由细化来减少推理偏差。对于生成任务，我们开发了一个框架，将ASR输出与大型语言模型（LLM）相结合，以生成连贯的、与上下文相关的更新，这些更新与预期的加强或削弱目标保持一致。此外，我们引入了一个新颖的基准数据集，带有加强/削弱标注和一个专门为评估生成性能而设计的基于LLM的评估指标。实验结果表明，我们的方法在增强VLMMs的动态推理能力方面取得了显著改进。
英文摘要：
Video Large Multimodal Models (VLMMs) have made impressive strides in understanding video content, but they often struggle with abstract and adaptive reasoning-the ability to revise their interpretations when new information emerges. In reality, conclusions are rarely set in stone; additional context can strengthen or weaken an initial inference. To address this, we introduce Defeasible Video Entailment (DVidE), a new task that challenges models to think like doubters, constantly updating their reasoning based on evolving evidence. In DVidE, given a video premise and a textual hypothesis, models must determine whether a new update strengthens or weakens the hypothesis (classification version) or generate a coherent update that modifies the entailment relationship (generation version). For solving the classification task, we propose the Chain of Counterfactual Thought framework, utilizing counterfactual reasoning, ASR-enhanced video content, and rationale refinement to reduce inference bias. For the generation task, we develop a framework that combines ASR output with a Large Language Model (LLM) to produce coherent, contextually relevant updates aligned with the intended strengthener or weakener goals. Additionally, we introduce a novel benchmark dataset, with strengthener/weakener annotations and an LLM-based evaluation metric specifically designed for assessing generative performance. Experimental results demonstrate significant improvements, highlighting our proposed method in enhancing dynamic reasoning capabilities of VLMMs.
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。
