Lune

ACL Findings2026

Geoparsing: Diagram Parsing for Plane and Solid Geometry with a Unified Formal Language

Peijie Wang, Ming-Liang Zhang, Jun Cao, Chao Deng, Dekang Ran, Pi Bu, Hongda Sun, Xuan Zhang, Yingyao Wang, Jun Song, Bo Zheng, Fei Yin, Cheng-Lin Liu

Abstract

Multimodal Large Language Models (MLLMs) have achieved remarkable progress but continue to struggle with geometric reasoning, primarily due to the perception bottleneck regarding fine-grained visual elements. While formal languages have aided plane geometry understanding, solid geometry which requires spatial understanding remains largely unexplored. In this paper, we address this challenge by designing a unified formal language that integrates plane and solid geometry, comprehensively covering geometric structures and semantic relations. We construct GDP-29K, a largescale dataset comprising 20k plane and 9k solid geometry samples collected from diverse realworld sources, each paired with its ground-truth formal description. To ensure syntactic correctness and geometric consistency, we propose a training paradigm that combines Supervised Fine-Tuning with Reinforcement Learning via Verifiable Rewards. Experiments show that our approach achieves state-of-the-art parsing performance. Furthermore, we demonstrate that our parsed formal descriptions serve as a critical cognitive scaffold, significantly boosting MLLMs' capabilities for downstream geometry reasoning tasks. Our data and code are available at Geoparsing.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems cites GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning
  • OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems cites MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
  • A Survey of Deep Learning for Geometry Problem Solving cites GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning
  • A Survey of Deep Learning for Geometry Problem Solving cites MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
  • G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model cites GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on8

  1. MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual ContextsPan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu et al.ICLR 2024 · 1,472 citations
  2. GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical ReasoningJiaqi Chen, Jianheng Tang, Jinghui Qin, Xiaodan Liang et al.ACL Findings 2021 · 114 citations
  3. OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific ProblemsChaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu et al.ACL 2024 · 18 citations
  4. A Survey of Deep Learning for Geometry Problem SolvingJianzhe Ma, Wenxuan Wang, Qin JinACL 2026 · 5 citations
  5. G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language ModelJiahui Gao, Renjie Pi, Jipeng Zhang, Jiacheng Ye et al.ICLR 2025 · 5 citations

Related papers

  1. Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic ReasoningRuoran Xu, Haoyu Cheng, Bin Dong, Qiufeng WangCVPR 2026 · 1 citation
  2. Concise Geometric Description as a Bridge: Unleashing the Potential of LLM for Plane Geometric Problem SolvingJingyun Wang, Dian Li, Xiaohan Wang, Gang Liu, Jiahong Yan, Guoliang KangCVPR Findings 2026
  3. GNS: Solving Plane Geometry Problems by Neural-Symbolic Reasoning with Multi-Modal LLMsMaizhen Ning, Zihao Zhou, Qiufeng Wang, Xiaowei Huang et al.AAAI 2025 · 10 citations
  4. Euclid’s Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate TasksShijie Lian, Changti Wu, Laurence Tianruo Yang, Hang Yuan, Bin Yu, Lei Zhang, Kai ChenCVPR Findings 2026
  5. GeoTikzBridge: Advancing Multimodal Code Generation for Geometric Perception and ReasoningJiayin Sun, Caixia Sun, Boyu Yang, hailin li et al.CVPR 2026 · 3 citations
Dusk over the sea between two cliffs drawn in fine vertical lines