LED Benchmark: Diagnosing Structural Layout Errors for Document Layout Analysis
This addresses the need for better evaluation of structural robustness in document layout analysis for researchers and practitioners, though it is incremental as it builds on existing benchmarks.
The paper tackles the problem of structural errors in document layout analysis by proposing the Layout Error Detection (LED) benchmark, which defines eight error types and three tasks, and experimental results show it effectively differentiates model capabilities and exposes biases not visible with traditional metrics.
Recent advancements in Document Layout Analysis through Large Language Models and Multimodal Models have significantly improved layout detection. However, despite these improvements, challenges remain in addressing critical structural errors, such as region merging, splitting, and missing content. Conventional evaluation metrics like IoU and mAP, which focus primarily on spatial overlap, are insufficient for detecting these errors. To address this limitation, we propose Layout Error Detection (LED), a novel benchmark designed to evaluate the structural robustness of document layout predictions. LED defines eight standardized error types, and formulates three complementary tasks: error existence detection, error type classification, and element-wise error type classification. Furthermore, we construct LED-Dataset, a synthetic dataset generated by injecting realistic structural errors based on empirical distributions from DLA models. Experimental results across a range of LMMs reveal that LED effectively differentiates structural understanding capabilities, exposing modality biases and performance trade-offs not visible through traditional metrics.