GeoEval: Benchmark for Evaluating LLMs and Multi-Modal Models on Geometry Problem-Solving
- URL: http://arxiv.org/abs/2402.10104v2
- Date: Fri, 17 May 2024 11:42:09 GMT
- Title: GeoEval: Benchmark for Evaluating LLMs and Multi-Modal Models on Geometry Problem-Solving
- Authors: Jiaxin Zhang, Zhongzhi Li, Mingliang Zhang, Fei Yin, Chenglin Liu, Yashar Moshfeghi,
- Abstract summary: We introduce the GeoEval benchmark, a comprehensive collection that includes a main subset of 2,000 problems, a 750 problems subset focusing on backward reasoning, an augmented subset of 2,000 problems, and a hard subset of 300 problems.
Our evaluation of ten LLMs and MMs across these varied subsets reveals that the WizardMath model excels, achieving a 55.67% accuracy rate on the main subset but only a 6.00% accuracy on the hard subset.
- Score: 40.46491587796371
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Recent advancements in large language models (LLMs) and multi-modal models (MMs) have demonstrated their remarkable capabilities in problem-solving. Yet, their proficiency in tackling geometry math problems, which necessitates an integrated understanding of both textual and visual information, has not been thoroughly evaluated. To address this gap, we introduce the GeoEval benchmark, a comprehensive collection that includes a main subset of 2,000 problems, a 750 problems subset focusing on backward reasoning, an augmented subset of 2,000 problems, and a hard subset of 300 problems. This benchmark facilitates a deeper investigation into the performance of LLMs and MMs in solving geometry math problems. Our evaluation of ten LLMs and MMs across these varied subsets reveals that the WizardMath model excels, achieving a 55.67\% accuracy rate on the main subset but only a 6.00\% accuracy on the hard subset. This highlights the critical need for testing models against datasets on which they have not been pre-trained. Additionally, our findings indicate that GPT-series models perform more effectively on problems they have rephrased, suggesting a promising method for enhancing model capabilities.
Related papers
- MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations [90.07275414500154]
We observe significant performance drops on MATH-P-Hard across various models.
We also raise concerns about a novel form of memorization where models blindly apply learned problem-solving skills.
arXiv Detail & Related papers (2025-02-10T13:31:46Z) - Improving Multimodal LLMs Ability In Geometry Problem Solving, Reasoning, And Multistep Scoring [34.37450586634531]
This paper presents GPSM4K, a comprehensive geometry multimodal dataset tailored to augment the problem-solving capabilities of Large Vision Language Models (LVLMs)
GPSM4K encompasses 2157 multimodal question-answer pairs manually extracted from mathematics textbooks spanning grades 7-12.
This dataset serves as an excellent benchmark for assessing the geometric reasoning capabilities of LVLMs.
arXiv Detail & Related papers (2024-12-01T15:19:23Z) - HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics [1.5716764919736026]
We introduce HARDMath, a dataset featuring challenging applied mathematics problems that require analytical approximation techniques.
Our framework auto-generates a large number of problems with solutions validated against numerical ground truths.
We evaluate both open- and closed-source LLMs on HARDMath-mini, a sub-sampled test set of 366 problems, as well as on 40 word problems formulated in applied science contexts.
arXiv Detail & Related papers (2024-10-13T20:09:41Z) - Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models [63.31878920079154]
We propose a benchmark specifically designed to assess large language models' mathematical reasoning at the Olympiad level.
Unlike existing Olympiad-related benchmarks, our dataset focuses exclusively on mathematics and comprises a vast collection of 4428 competition-level problems with rigorous human annotation.
Our experimental results show that even the most advanced models, OpenAI o1-mini and OpenAI o1-preview, struggle with highly challenging Olympiad-level problems, with 60.54% and 52.55% accuracy, highlighting significant challenges in Olympiad-level mathematical reasoning.
arXiv Detail & Related papers (2024-10-10T14:39:33Z) - ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection [60.297079601066784]
We introduce ErrorRadar, the first benchmark designed to assess MLLMs' capabilities in error detection.
ErrorRadar evaluates two sub-tasks: error step identification and error categorization.
It consists of 2,500 high-quality multimodal K-12 mathematical problems, collected from real-world student interactions.
Results indicate significant challenges still remain, as GPT-4o with best performance is still around 10% behind human evaluation.
arXiv Detail & Related papers (2024-10-06T14:59:09Z) - MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models Using Odyssey Math Data [20.31528845718877]
Large language models (LLMs) have significantly advanced natural language understanding and demonstrated strong problem-solving abilities.
This paper investigates the mathematical problem-solving capabilities of LLMs using the newly developed "MathOdyssey" dataset.
arXiv Detail & Related papers (2024-06-26T13:02:35Z) - MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Time [51.5039731721706]
MindStar is a purely inference-based searching method for large language models.
It formulates reasoning tasks as searching problems and proposes two search ideas to identify the optimal reasoning paths.
It significantly enhances the reasoning abilities of open-source models, such as Llama-2-13B and Mistral-7B, and achieves comparable performance to GPT-3.5 and Grok-1.
arXiv Detail & Related papers (2024-05-25T15:07:33Z) - GeomVerse: A Systematic Evaluation of Large Models for Geometric
Reasoning [17.61621287003562]
We evaluate vision language models (VLMs) along various axes through the lens of geometry problems.
We procedurally create a synthetic dataset of geometry questions with controllable difficulty levels along multiple axes.
The empirical results obtained using our benchmark for state-of-the-art VLMs indicate that these models are not as capable in subjects like geometry.
arXiv Detail & Related papers (2023-12-19T15:25:39Z) - G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model [124.68242155098189]
Large language models (LLMs) have shown remarkable proficiency in human-level reasoning and generation capabilities.
G-LLaVA demonstrates exceptional performance in solving geometric problems, significantly outperforming GPT-4-V on the MathVista benchmark with only 7B parameters.
arXiv Detail & Related papers (2023-12-18T17:36:20Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.