arXiv:2405.18433
Notes on Applicability of GPT-4 to Document Understanding
원문 초록
We perform a missing, reproducible evaluation of all publicly available GPT-4 family models concerning the Document Understanding field, where it is frequently required to comprehend text spacial arrangement and visual clues in addition to textual semantics. Benchmark results indicate that though it is hard to achieve satisfactory results with text-only models, GPT-4 Vision Turbo performs well when one provides both text recognized by an external OCR engine and document images on the input. Evaluation is followed by analyses that suggest possible contamination of textual GPT-4 models and indicate the significant performance drop for lengthy documents.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
PaddleOCR 3.0 Technical Report
DrishtiKon: Multi-Granular Visual Grounding for Text-Rich Document Images
ARB: A Comprehensive Arabic Multimodal Reasoning Benchmark
Evaluating Menu OCR and Translation: A Benchmark for Aligning Human and Automated Evaluations in Large Vision-Language Models
Relation-Rich Visual Document Generator for Visual Information Extraction
BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata Extraction
토론
이 논문과 연결된 포럼 글이 아직 없습니다.