UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908990589370368 |
|---|---|
| author | Ji, Yifan Xu, Zhipeng Liu, Zhenghao Chen, Zulong Zhang, Qian Yang, Zhibo Lin, Junyang Gu, Yu Yu, Ge Sun, Maosong |
| author_facet | Ji, Yifan Xu, Zhipeng Liu, Zhenghao Chen, Zulong Zhang, Qian Yang, Zhibo Lin, Junyang Gu, Yu Yu, Ge Sun, Maosong |
| contents | Key Information Extraction (KIE) from real-world documents remains challenging due to substantial variations in layout structures, visual quality, and task-specific information requirements. Recent Large Multimodal Models (LMMs) have shown promising potential for performing end-to-end KIE directly from document images. To enable a comprehensive and systematic evaluation across realistic and diverse application scenarios, we introduce UNIKIE-BENCH, a unified benchmark designed to rigorously evaluate the KIE capabilities of LMMs. UNIKIE-BENCH consists of two complementary tracks: a constrained-category KIE track with scenario-predefined schemas that reflect practical application needs, and an open-category KIE track that extracts any key information that is explicitly present in the document. Experiments on 15 state-of-the-art LMMs reveal substantial performance degradation under diverse schema definitions, long-tail key fields, and complex layouts, along with pronounced performance disparities across different document types and scenarios. These findings underscore persistent challenges in grounding accuracy and layout-aware reasoning for LMM-based KIE. All codes and datasets are available at https://github.com/NEUIR/UNIKIE-BENCH. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_07038 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents Ji, Yifan Xu, Zhipeng Liu, Zhenghao Chen, Zulong Zhang, Qian Yang, Zhibo Lin, Junyang Gu, Yu Yu, Ge Sun, Maosong Computer Vision and Pattern Recognition Computation and Language Key Information Extraction (KIE) from real-world documents remains challenging due to substantial variations in layout structures, visual quality, and task-specific information requirements. Recent Large Multimodal Models (LMMs) have shown promising potential for performing end-to-end KIE directly from document images. To enable a comprehensive and systematic evaluation across realistic and diverse application scenarios, we introduce UNIKIE-BENCH, a unified benchmark designed to rigorously evaluate the KIE capabilities of LMMs. UNIKIE-BENCH consists of two complementary tracks: a constrained-category KIE track with scenario-predefined schemas that reflect practical application needs, and an open-category KIE track that extracts any key information that is explicitly present in the document. Experiments on 15 state-of-the-art LMMs reveal substantial performance degradation under diverse schema definitions, long-tail key fields, and complex layouts, along with pronounced performance disparities across different document types and scenarios. These findings underscore persistent challenges in grounding accuracy and layout-aware reasoning for LMM-based KIE. All codes and datasets are available at https://github.com/NEUIR/UNIKIE-BENCH. |
| title | UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2602.07038 |