从答案到理据：采用面向答案的思维链进行自对齐多模态推理
From Answers to Rationales: Self-Aligning Multimodal Reasoning with Answer-Oriented Chain-of-Thought
AI总结：
本文提出SMART框架，利用面向答案的思维链从正确与错误答案自动构建正负理据数据，并通过迭代生成—优化提升多模态大语言模型推理能力。
摘要：
在多模态大语言模型（MLLM）中实现类人推理能力长期以来一直是一个目标。当前方法主要关注合成正理据，通常依赖人工标注或复杂系统。此外，它们往往忽视负向推理，这限制了模型在多模态推断中的泛化能力和鲁棒性。为弥补这一空白，我们提出了一个新颖框架：采用面向答案的思维链进行自对齐多模态推理（SMART）。SMART使用面向答案的思维链（AoT）提示来自动构建高质量数据。受人类基于证明的策略启发，AoT同时利用正确和错误答案，以提取连接问题与答案的关键视觉信息。当提供正确答案时，模型生成强有力的正理据。相反，当正确答案被错误选项替换时，模型会生成一条错误却具有说服力的推理路径，作为一种判别性负理据。使用AoT生成数据训练的模型优于在人工标注数据集上训练的模型，展现出更强的推理能力。因此，SMART建立了一种迭代生成—优化方法，可持续增强模型的推理技能。实验表明，无论模型架构、参数规模或预训练数据集如何，SMART框架都能显著改进多种MLLM。代码可在https://github.com/WentaoTan/SMART获取。
英文摘要：
Achieving human-like reasoning capabilities in Multimodal Large Language Models (MLLMs) has long been a goal. Current methods primarily focus on synthesizing positive rationales, typically relying on manual annotations or complex systems. Moreover, they often overlook negative reasoning, which limits the model's generalization ability and robustness in multimodal inference. To address this gap, we propose a novel framework: \textbf{S}elf-Aligning \textbf{M}ultimodal Reasoning with \textbf{A}nswer-O\textbf{r}iented Chain-of-\textbf{T}hought (SMART). SMART employs an answer-oriented chain-of-thought (AoT) prompt to automatically construct high-quality data. Drawing inspiration from human proof-based strategies, AoT leverages both correct and incorrect answers to extract key visual information that links questions and answers. When provided with correct answers, the model produces strong positive rationales. Conversely, when correct answers are replaced with incorrect alternatives, the model generates an erroneous yet compelling reasoning path, serving as a form of discriminative negative rationale. Models trained with AoT-generated data outperform those trained on manually annotated datasets, demonstrating superior reasoning capabilities. Consequently, SMART establishes an iterative generation-optimization method that continually enhances the model's reasoning skills. Experiments indicate that the SMART framework significantly improves various MLLMs, regardless of model architecture, parameter size, or pre-training dataset. The code is available at https://github.com/WentaoTan/SMART.
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。
