基于最大可满足性的反馈在数独中引导视觉语言模型
MaxSAT-Based Feedback for Guiding Vision-Language Models in Sudoku
浏览论文内容
中文总结 AI 辅助
研究在数独中引导视觉语言模型的问题，提出通过MaxSAT预言机将形式约束推理集成到VLM求解过程的神经符号方法，经实验验证该方法能提高逻辑一致性和解决实例数量，增强视觉语言推理可靠性。
中文摘要 AI 辅助
视觉语言模型（VLM）在结构化视觉推理任务中展现出良好性能，但缺乏执行逻辑一致性的明确机制，常生成违反潜在约束的赋值。本文提出一种神经符号方法，通过最大可满足性（MaxSAT）预言机将形式约束推理集成到VLM求解过程。符号组件充当一致性验证器和优化引擎，VLM生成的候选位置编码为部分MaxSAT公式中的软子句，数独约束为硬子句。不一致时，MaxSAT求解器识别最大一致赋值子集并转化为反馈指导后续优化。在数独数据集上评估，结果表明基于MaxSAT的反馈提高了逻辑一致性和解决实例数量，证明符号优化可增强视觉语言推理的可靠性。
英文摘要
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 frequently generate assignments that violate underlying constraints. In this paper, we propose a neuro-symbolic approach that integrates formal constraint reasoning into the VLM solving process via a Maximum Satisfiability (MaxSAT) oracle. Rather than computing solutions directly, the symbolic component acts as a consistency validator and refinement engine. Candidate placements generated by the VLM are encoded as soft clauses in a partial MaxSAT formulation, while Sudoku constraints remain hard clauses. When inconsistencies arise, the MaxSAT solver identifies a largest mutually consistent subset of assignments, which is then translated into structured textual and visual feedback to guide subsequent refinements. We evaluate our approach on a Sudoku dataset across multiple open-source and closed-access VLMs. Results show that MaxSAT-based feedback improves logical consistency and increases the number of solved instances, particularly in full-board refinement mode. These findings demonstrate that symbolic optimisation can enhance the reliability of vision-language reasoning.
发表机构
- Artificial Intelligence Research Institute (IIIA), Consejo Superior de Investigaciones Científicas (CSIC)（人工智能研究所（IIIA），西班牙科学研究高级理事会（CSIC））
- Institut de Robòtica i Informàtica Industrial (IRI-CSIC-UPC)（工业机器人与信息学研究所（IRI-CSIC-UPC））
机构由 AI 辅助整理，请以论文原文为准。
