Can Vision-Language Models Evaluate Handwritten Math?

• URL: http://arxiv.org/abs/2501.07244v2
• Date: Wed, 12 Mar 2025 04:10:33 GMT
• Title: Can Vision-Language Models Evaluate Handwritten Math?
• Abstract summary: FERMAT is a benchmark designed to assess the ability of Vision-Language Models to detect, localize and correct errors in handwritten content.<n>We benchmark nine VLMs across three tasks: error detection, localization, and correction.<n>Our results reveal significant shortcomings in current VLMs in reasoning over handwritten text, with Gemini-1.5-Pro achieving the highest error correction rate.
• Score: 17.350707580013054
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advancements in Vision-Language Models (VLMs) have opened new possibilities in automatic grading of handwritten student responses, particularly in mathematics. However, a comprehensive study to test the ability of VLMs to evaluate and reason over handwritten content remains absent. To address this gap, we introduce FERMAT, a benchmark designed to assess the ability of VLMs to detect, localize and correct errors in handwritten mathematical content. FERMAT spans four key error dimensions - computational, conceptual, notational, and presentation - and comprises over 2,200 handwritten math solutions derived from 609 manually curated problems from grades 7-12 with intentionally introduced perturbations. Using FERMAT we benchmark nine VLMs across three tasks: error detection, localization, and correction. Our results reveal significant shortcomings in current VLMs in reasoning over handwritten text, with Gemini-1.5-Pro achieving the highest error correction rate (77%). We also observed that some models struggle with processing handwritten content, as their accuracy improves when handwritten inputs are replaced with printed text or images. These findings highlight the limitations of current VLMs and reveal new avenues for improvement. We release FERMAT and all the associated resources in the open-source to drive further research.

Related papers

• Automated Grading of Handwritten Mathematics Using Vision-Capable LLMs [2.727845763576068]
  Vision-capable large language models (LLMs) offer new opportunities.<n>We present an empirical evaluation of an LLM-based grader for handwritten mathematical work using instructor-defined rubrics.
  arXiv  Detail & Related papers  (2026-05-18T19:06:15Z)
• When VLMs 'Fix' Students: Identifying and Penalizing Over-Correction in the Evaluation of Multi-line Handwritten Math OCR [1.625123212387532]
  We present the first systematic study of multi-line handwritten math OCR, revealing a critical failure mode of Vision-Language Models (VLMs)<n>Instead of faithfully transcribing a student's work, these models often "fix" errors, thereby hiding the very mistakes an educational assessment aims to detect.<n>We propose PINK, a semantic evaluation metric that leverages a Large Language Model (LLM) for rubric-based grading and explicitly penalizes over-correction.
  arXiv  Detail & Related papers  (2026-04-01T05:27:52Z)
• Can MLLMs Read Students' Minds? Unpacking Multimodal Error Analysis in Handwritten Math [55.83696908107408]
  We introduce ScratchMath, a novel benchmark for explaining and classifying errors in authentic handwritten mathematics scratchwork.<n>Our dataset comprises 1,720 mathematics samples from Chinese primary and middle school students.<n>We systematically evaluate 16 leading MLLMs on ScratchMath, revealing significant performance gaps relative to human experts.
  arXiv  Detail & Related papers  (2026-03-26T02:57:20Z)
• MMErroR: A Benchmark for Erroneous Reasoning in Vision-Language Models [29.830224745428566]
  We present MMErroR, a benchmark of 2,013 samples each embedding a single coherent reasoning error.<n>Unlike existing benchmarks that focus on answer correctness, MMErroR targets a process-level, error-centric evaluation.<n>We evaluate 20 advanced Vision-Language Models, even the best model (Gemini-3.0-Pro) classifies the error in only 66.47% of cases.
  arXiv  Detail & Related papers  (2026-01-06T17:45:26Z)
• Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences [2.7405470973070547]
  Conversion of spoken mathematical expressions is a challenging task that involves transcribing speech into a strictly structured symbolic representation.<n>We present the first fully open-source large-scale dataset, comprising over 66,000 human-annotated audio samples of mathematical equations and sentences.
  arXiv  Detail & Related papers  (2025-08-05T15:11:37Z)
• Evaluating GPT-4 at Grading Handwritten Solutions in Math Exams [48.99818550820575]
  We leverage state-of-the-art multi-modal AI models, in particular GPT-4o, to automatically grade handwritten responses to college-level math exams. Using real student responses to questions in a probability theory exam, we evaluate GPT-4o's alignment with ground-truth scores from human graders using various prompting techniques.
  arXiv  Detail & Related papers  (2024-11-07T22:51:47Z)
• DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models [19.787224412654872]
  We introduce DynaMath, a dynamic visual math benchmark designed for in-depth assessment of Vision-Language Models (VLMs) DynaMath includes 501 high-quality, multi-topic seed questions, each represented as a Python program. Our results show that the worst-case model accuracy, defined as the percentage of correctly answered seed questions in all 10 variants, is significantly lower than the average-case accuracy.
  arXiv  Detail & Related papers  (2024-10-29T17:29:19Z)
• Subtle Errors Matter: Preference Learning via Error-injected Self-editing [59.405145971637204]
  We propose a novel preference learning framework called eRror-Injected Self-Editing (RISE) RISE injects predefined subtle errors into pivotal tokens in reasoning or steps to construct hard pairs for error mitigation. Experiments validate the effectiveness of RISE, with preference learning on Qwen2-7B-Instruct yielding notable improvements of 3.0% on GSM8K and 7.9% on MATH with only 4.5K training samples.
  arXiv  Detail & Related papers  (2024-10-09T07:43:38Z)
• Vision-Language Model Based Handwriting Verification [23.983430206133793]
  This paper explores using Vision Language Models (VLMs), such as OpenAI's GPT-4o and Google's PaliGemma, to address these challenges. Our goal is to provide clear, human-understandable explanations for model decisions.
  arXiv  Detail & Related papers  (2024-07-31T17:57:32Z)
• MUSE: Machine Unlearning Six-Way Evaluation for Language Models [109.76505405962783]
  Language models (LMs) are trained on vast amounts of text data, which may include private and copyrighted content. We propose MUSE, a comprehensive machine unlearning evaluation benchmark. We benchmark how effectively eight popular unlearning algorithms can unlearn Harry Potter books and news articles.
  arXiv  Detail & Related papers  (2024-07-08T23:47:29Z)
• DiVERT: Distractor Generation with Variational Errors Represented as Text for Math Multiple-choice Questions [42.148511874019256]
  We introduce DiVERT, a novel variational approach that learns an interpretable representation of errors behind distractors in math multiple-choice questions (MCQs) We show that DiVERT, despite using a base open-source LLM with 7B parameters, outperforms state-of-the-art approaches using GPT-4o on downstream distractor generation. We also conduct a human evaluation with math educators and find that DiVERT leads to error labels that are of comparable quality to human-authored ones.
  arXiv  Detail & Related papers  (2024-06-27T17:37:31Z)
• LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback [71.95402654982095]
  We propose Math-Minos, a natural language feedback-enhanced verifier. Our experiments reveal that a small set of natural language feedback can significantly boost the performance of the verifier.
  arXiv  Detail & Related papers  (2024-06-20T06:42:27Z)
• MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems? [99.0305256706604]
  We introduce MathVerse, an all-around visual math benchmark designed for an equitable and in-depth evaluation of MLLMs. We meticulously collect 2,612 high-quality, multi-subject math problems with diagrams from publicly available sources. This approach allows MathVerse to comprehensively assess whether and how much MLLMs can truly understand the visual diagrams for mathematical reasoning.
  arXiv  Detail & Related papers  (2024-03-21T17:59:50Z)
• Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning [90.13978453378768]
  We introduce a comprehensive typology of factual errors in generated chart captions. A large-scale human annotation effort provides insight into the error patterns and frequencies in captions crafted by various chart captioning models. Our analysis reveals that even state-of-the-art models, including GPT-4V, frequently produce captions laced with factual inaccuracies.
  arXiv  Detail & Related papers  (2023-12-15T19:16:21Z)
• CMATH: Can Your Language Model Pass Chinese Elementary School Math Test? [15.53530547827583]
  We present the Chinese Elementary School Math Word Problems dataset, comprising 1.7k elementary school-level math word problems with detailed annotations. This dataset aims to provide a benchmark tool for assessing the abilities of popular large language models (LLMs) We evaluate a variety of popular LLMs, including both commercial and open-source options, and discover that only GPT-4 achieves success (accuracy $geq$ 60%) across all six elementary school grades.
  arXiv  Detail & Related papers  (2023-06-29T02:19:50Z)
• MISMATCH: Fine-grained Evaluation of Machine-generated Text with Mismatch Error Types [68.76742370525234]
  We propose a new evaluation scheme to model human judgments in 7 NLP tasks, based on the fine-grained mismatches between a pair of texts. Inspired by the recent efforts in several NLP tasks for fine-grained evaluation, we introduce a set of 13 mismatch error types. We show that the mismatch errors between the sentence pairs on the held-out datasets from 7 NLP tasks align well with the human evaluation.
  arXiv  Detail & Related papers  (2023-06-18T01:38:53Z)

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.