SpatialMath: Spatial Comprehension-Infused Symbolic Reasoning for Mathematical Problem-Solving
Multimodal Small-to-Medium sized Language Models (MSLMs) have demonstrated strong capabilities in integrating visual and textual information but still face significant limitations in visual comprehension and mathematical reasoning, particularly in geometric problems with diverse levels of visual infusion. Current models struggle to accurately decompose intricate visual inputs and connect perception with structured reasoning, leading to suboptimal performance. To address these challenges, we propose SpatialMath, a novel Spatial Comprehension-Infused Symbolic Reasoning Framework designed to integrate spatial representations into structured symbolic reasoning chains. SpatialMath employs a specialized perception module to extract spatially-grounded representations from visual diagrams, capturing critical geometric structures and spatial relationships. These representations are then methodically infused into symbolic reasoning chains, facilitating visual comprehension-aware structured reasoning. To this end, we introduce MATHVERSE-PLUS, a novel dataset containing structured visual interpretations and step-by-step reasoning paths for vision-intensive mathematical problems. SpatialMath significantly outperforms strong multimodal baselines, achieving up to 10 percentage points improvement over supervised fine-tuning with data augmentation in vision-intensive settings. Robustness analysis reveals that enhanced spatial representations directly improve reasoning accuracy, reinforcing the need for structured perception-to-reasoning pipelines in MSLMs.
Code (0)
등록된 구현이 없습니다.
Tasks
Mathematical ReasoningData AugmentationSimilar Papers 제목 키워드 기반
VIRO: Robust and Efficient Neuro-Symbolic Reasoning with Verification for Referring Expression Comprehension
Referring Expression Comprehension (REC) aims to localize the image region corresponding to a natural language query. Recent neuro-symbolic REC approaches leverage large language models (LLMs) and vision-language models …
Zero-shot GeneralizationReferring ExpressionTowards a Neurosymbolic Reasoning System Grounded in Schematic Representations
Despite significant progress in natural language understanding, Large Language Models (LLMs) remain error-prone when performing logical reasoning, often lacking the robust mental representations that enable human-like co…
Natural Language UnderstandingSpatial ReasoningLogical ReasoningSpatial Knowledge-Infused Hierarchical Learning: An Application in Flood Mapping on Earth Imagery
Deep learning for Earth imagery plays an increasingly important role in geoscience applications such as agriculture, ecology, and natural disaster management. Still, progress is often hindered by the limited training lab…
Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks
Language models' (LMs) proficiency in handling deterministic symbolic reasoning and rule-based tasks remains limited due to their dependency implicit learning on textual data. To endow LMs with genuine rule comprehension…
Arithmetic ReasoningLanguage ModellingAdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension
Recent machine reading comprehension datasets such as ReClor and LogiQA require performing logical reasoning over text. Conventional neural models are insufficient for logical reasoning, while symbolic reasoners cannot d…
Logical ReasoningMachine Reading ComprehensionMultiple-choiceReading Comprehension