研究人员开发了一种新颖的神经符号方法，以提高视觉语言模型（VLMs）在解决数独等基于网格的谜题时的逻辑一致性。该方法集成了最大可满足性（MaxSAT）预言机，作为VLM生成赋值的验证器和精炼引擎。通过将候选放置编码为软子句，并将数独约束编码为硬子句，MaxSAT求解器在出现不一致时识别出最大的相互一致的赋值子集。这种以结构化文本和视觉格式提供的反馈，指导VLMs提高逻辑一致性并增加解决谜题的成功率。 AI
影响 这种方法可能导致更可靠、逻辑上更一致的AI系统，用于复杂的推理任务。
排序理由 这是一篇研究论文，详细介绍了一种提高AI模型在特定任务上性能的新方法。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2607.12711v1 Announce Type: new Abstract: Vision--Language Models (VLMs) have recently demonstrated promising performance on structured visual reasoning tasks, including grid-based puzzles. However, despite strong perceptual capabilities, these models lack explicit mechanis…
Vision--Language Models (VLMs) have recently demonstrated promising performance on structured visual reasoning tasks, including grid-based puzzles. However, despite strong perceptual capabilities, these models lack explicit mechanisms for enforcing logical consistency and frequen…