paper-with-me

Papers

SpatialMath: Spatial Comprehension-Infused Symbolic Reasoning for Mathematical Problem-Solving

2026-01-24 · Ashutosh Bajpai, Akshat Bhandari, Akshay Nambi, Tanmoy Chakraborty arxiv

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.

📄 PDF Abstract BibTeX arXiv:2601.17489

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical ReasoningData Augmentation

Similar Papers 제목 키워드 기반

VIRO: Robust and Efficient Neuro-Symbolic Reasoning with Verification for Referring Expression Comprehension

2026-01-19 · Hyejin Park, Junhyuk Kwon, Suha Kwak, Jungseul Ok arxiv

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 Expression

Towards a Neurosymbolic Reasoning System Grounded in Schematic Representations

2025-09-03 · François Olivier, Zied Bouraoui arxiv

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 Reasoning

Spatial Knowledge-Infused Hierarchical Learning: An Application in Flood Mapping on Earth Imagery

2023-12-12 · Zelin Xu, Tingsong Xiao, Wenchong He, Yu Wang 외

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

2023-04-04 · Yixuan Weng, Minjun Zhu, Fei Xia, Bin Li 외

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 Modelling

AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension

2022-03-16 · ACL 2022 5 · Xiao Li, Gong Cheng, Ziheng Chen, Yawei Sun 외

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