mlsanityData to 14 Oct 2026

HG-Bench: A Benchmark for Multi-Page Handwritten Answer-Region Grounding in Automated Homework Assessment

arXiv 2606.25491 ↗First posted 24 Jun 2026cs.CV cs.AIcited by 0

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

Automated homework assessment depends not only on recognizing student answers, but also on accurately locating where each answer and each intermediate reasoning step appears in noisy, multi-page handwritten work. This paper addresses the missing evaluation setting of page-aware, two-level answer-region grounding: given a sequence of homework page images, a model must localize complete answer regions and their ordered step-level subregions. We introduce HG-Bench, a benchmark of 500 human-annotated K-12 homework samples curated from a 1,489,278-image source pool, with question-level and step-level boxes linked by a hierarchical containment constraint. HG-Bench is paired with a page-aware evaluation protocol that separately measures complete-answer localization (FA) and step-level decomposition (FSm), revealing whether models truly ground the spatial structure of student reasoning rather than merely parse visible text. Across frontier closed-source APIs and competitive open-weight VLMs, no zero-shot system exceeds 55.22% on FA or 48.22% on FSm, while a GLM-4.6V 9B reference model fine-tuned on ~10k in-domain examples reaches 74.97/72.26. These results identify step-level handwritten grounding as a concrete capability gap and provide a reproducible benchmark, evaluation protocol, and trained reference point for future work on automated homework assessment.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 40 of its 53 references that are in the map. First posted on arXiv 24 Jun 2026.

Builds on

40 of 53 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning1 Jul
  2. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling6 Dec
  3. 2024We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?1 Jul
  4. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts3 Oct
  5. 2023MMBench: Is Your Multi-modal Model an All-around Player?12 Jul
  6. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning19 Mar

Other references · 34

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2025Qwen2.5-VL Technical Reportcited by 5,587
  3. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  5. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  6. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  7. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  8. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  9. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  10. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  11. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  12. 2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,362
22 more
  1. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,317
  2. 2021Grounded Language-Image Pre-trainingcited by 1,156
  3. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,136
  4. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  5. 2016Modeling Context in Referring Expressionscited by 1,063
  6. 2023SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehensioncited by 940
  7. 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magiccited by 906
  8. 2015Generation and Comprehension of Unambiguous Object Descriptionscited by 904
  9. 2024DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Modelscited by 867
  10. 2024MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?cited by 586
  11. 2024DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understandingcited by 572
  12. 2023Ferret: Refer and Ground Anything Anywhere at Any Granularitycited by 509
  13. 2026Kimi K2.5: Visual Agentic Intelligencecited by 501
  14. 2022LayoutLMv3: Pre-training for Document AI with Unified Text and Image Maskingcited by 485
  15. 2021InfographicVQAcited by 437
  16. 2023Florence-2: Advancing a Unified Representation for a Variety of Vision Taskscited by 410
  17. 2021OCR-free Document Understanding Transformercited by 407
  18. 2025Seed1.5-VL Technical Reportcited by 373
  19. 2022Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understandingcited by 366
  20. 2019FUNSD: A Dataset for Form Understanding in Noisy Scanned Documentscited by 349
  21. 2024CogVLM2: Visual Language Models for Image and Video Understandingcited by 217
  22. 2023UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Modelcited by 143

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Towards Fully Automated Exam Grading: Fairness-Aware Recognition of Handwritten Answers with Foundation Models
  2. 2025Evaluating Vision-Language and Large Language Models for Automated Student Assessment in Indonesian Classrooms
  3. 2026DocAttriBench: Benchmarking Answer Grounding in Document Visual Question Answering
  4. 2025DocVAL: Validated Chain-of-Thought Distillation for Grounded Document VQA
  5. 2026Evaluating AI Grading on Real-World Handwritten College Mathematics: A Large-Scale Study Toward a Benchmark
  6. 2026Human-Grounded Multimodal Benchmark with 900K-Scale Aggregated Student Response Distributions from Japan's National Assessment of Academic Ability
  7. 2025Comparing RAG and GraphRAG for Page-Level Retrieval Question Answering on a Math Textbook
  8. 2026GRACE: Grounded Reasoning via Adapter Composition and Evidence-Aware Calibration for Educational Visual Question Answering