SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding
2026-07-11 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors created SynthDocBench, a new test set made entirely of fake documents designed to vary factors like length, layout, and question type independently. This helps them figure out why vision language models (VLMs) struggle with understanding complex documents. Testing seven top VLMs, they found that these models perform worse as documents get longer, have trouble with the middle parts of documents, and struggle with charts in long documents. Their work suggests current models might be learning shortcuts from existing tests instead of truly understanding long, complex documents.
Vision Language ModelsVisual Document UnderstandingBenchmarkSynthetic DataLong-Context DocumentsDocument LayoutModalityPositional SensitivityChart ComprehensionModel Evaluation
Authors
Abhigya Verma, Khyati Mahajan, Amit Kumar Saha, Shruthan Radhakrishna, Sagar Davasam, Vikas Yadav, Sai Rajeswar Mudumba
Abstract
Vision language models (VLMs) have achieved strong performance on visual document understanding benchmarks such as DocVQA, ChartQA, and MMLongBench-Doc. However, real-world documents combine multiple factors such as length, layout complexity, modality, and question difficulty, which makes it difficult to attribute model failures to specific causes. We introduce SynthDocBench, a fully synthetic benchmark for long-context visual document understanding that systematically controls factors including document length, layout structure, modality composition, and question type. The benchmark is constructed using a combinatorial design, each factor is varied independently across generated documents, enabling controlled analysis of model behavior. Documents are generated end to end using an LLM pipeline across six layout archetypes, with a 40 percent random override to prevent models from exploiting spurious correlations. Additionally, SynthDocBench spans long-context documents with substantially greater length and structural diversity than existing benchmarks. Evaluating seven frontier VLMs, we uncover three failure modes that existing benchmarks cannot surface: sharp degradation with document length, a systematic positional sensitivity in which the middle third of a document is hardest for five of six models and five of six models show a negative Early-to-Late trend (steepest decline: 8.3 percentage points), and breakdown of chart comprehension in long-document settings. These results suggest that current models may be overfitting to benchmark artifacts rather than achieving robust long-context visual document understanding.