中文
相关论文

相关论文: Evaluating Robustness of LLMs in Question Answerin…

200 篇论文

Academic documents are packed with texts, equations, tables, and figures, requiring comprehensive understanding for accurate Optical Character Recognition (OCR). While end-to-end OCR methods offer improved accuracy over layout-based…

计算机视觉与模式识别 · 计算机科学 2024-03-05 Yu Sun , Dongzhan Zhou , Chen Lin , Conghui He , Wanli Ouyang , Han-Sen Zhong

Despite recent advances, standard sequence labeling systems often fail when processing noisy user-generated text or consuming the output of an Optical Character Recognition (OCR) process. In this paper, we improve the noise-aware training…

计算与语言 · 计算机科学 2021-05-26 Marcin Namysl , Sven Behnke , Joachim Köhler

The digitisation of historical print media archives is crucial for increasing accessibility to contemporary records. However, the process of Optical Character Recognition (OCR) used to convert physical records to digital text is prone to…

计算与语言 · 计算机科学 2025-01-23 Jonathan Bourne

The inherent complexities of Arabic script; its cursive nature, diacritical marks (tashkeel), and varied typography, pose persistent challenges for Optical Character Recognition (OCR). We present Qari-OCR, a series of vision-language models…

计算机视觉与模式识别 · 计算机科学 2025-06-04 Ahmed Wasfy , Omer Nacar , Abdelakreem Elkhateb , Mahmoud Reda , Omar Elshehy , Adel Ammar , Wadii Boulila

Large Multimodal Models (LMMs) have become increasingly versatile, accompanied by impressive Optical Character Recognition (OCR) related capabilities. Existing OCR-related benchmarks emphasize evaluating LMMs' abilities of relatively simple…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Haibin He , Maoyuan Ye , Jing Zhang , Xiantao Cai , Juhua Liu , Bo Du , Dacheng Tao

Scoring the Optical Character Recognition (OCR) capabilities of Large Multimodal Models (LMMs) has witnessed growing interest. Existing benchmarks have highlighted the impressive performance of LMMs in text recognition; however, their…

Reading comprehension by machine has been widely studied, but machine comprehension of spoken content is still a less investigated problem. In this paper, we release Open-Domain Spoken Question Answering Dataset (ODSQA) with more than three…

计算与语言 · 计算机科学 2018-08-08 Chia-Hsuan Lee , Shang-Ming Wang , Huan-Cheng Chang , Hung-Yi Lee

Digital humanities scholars increasingly use Large Language Models for historical document digitization, yet lack appropriate evaluation frameworks for LLM-based OCR. Traditional metrics fail to capture temporal biases and period-specific…

计算机视觉与模式识别 · 计算机科学 2025-10-09 Maria Levchenko

Recent advancements in multimodal slow-thinking systems have demonstrated remarkable performance across various visual reasoning tasks. However, their capabilities in text-rich image reasoning tasks remain understudied due to the absence of…

机器学习 · 计算机科学 2026-05-27 Mingxin Huang , Yongxin Shi , Dezhi Peng , Songxuan Lai , Zecheng Xie , Lianwen Jin

We explore how multimodal Large Language Models (mLLMs) can help researchers transcribe historical documents, extract relevant historical information, and construct datasets from historical sources. Specifically, we investigate the…

计算与语言 · 计算机科学 2025-04-02 Gavin Greif , Niclas Griesshaber , Robin Greif

While OCR has been used in various applications, its output is not always accurate, leading to misfit words. This research work focuses on improving the optical character recognition (OCR) with ML techniques with integration of OCR with…

计算机视觉与模式识别 · 计算机科学 2023-04-18 Abhishek Bamotra , Phani Krishna Uppala

We investigate OCR-augmented generation with Vision Language Models (VLMs), exploring tasks in Korean and English toward multilingualism. To support research in this domain, we train and release KLOCR, a strong bilingual OCR baseline…

计算机视觉与模式识别 · 计算机科学 2025-10-06 JoonHo Lee , Sunho Park

Large Vision-Language Models (VLMs) have demonstrated significant potential on complex visual understanding tasks through iterative optimization methods.However, these models generally lack effective self-correction mechanisms, making it…

计算机视觉与模式识别 · 计算机科学 2026-02-25 Shimin Wen , Zeyu Zhang , Xingdou Bian , Hongjie Zhu , Lulu He , Layi Shama , Daji Ergu , Ying Cai

Conventional Optical Character Recognition (OCR) systems are challenged by variant invoice layouts, handwritten text, and low-quality scans, which are often caused by strong template dependencies that restrict their flexibility across…

计算机视觉与模式识别 · 计算机科学 2026-01-09 Khushi Khanchandani , Advait Thakur , Akshita Shetty , Chaitravi Reddy , Ritisa Behera

Optical character recognition (OCR) and document understanding systems increasingly rely on large vision and vision-language models, yet evaluation remains centered on modern, Western, and institutional documents. This emphasis masks system…

计算机视觉与模式识别 · 计算机科学 2026-03-30 Fitsum Sileshi Beyene , Christopher L. Dancy

This paper introduces an open-source benchmark for evaluating Vision-Language Models (VLMs) on Optical Character Recognition (OCR) tasks in dynamic video environments. We present a curated dataset containing 1,477 manually annotated frames…

计算机视觉与模式识别 · 计算机科学 2025-02-11 Sankalp Nagaonkar , Augustya Sharma , Ashish Choithani , Ashutosh Trivedi

Current ophthalmology clinical workflows are plagued by over-referrals, long waits, and complex and heterogeneous medical records. Large language models (LLMs) present a promising solution to automate various procedures such as triaging,…

Thousands of users consult digital archives daily, but the information they can access is unrepresentative of the diversity of documentary history. The sequence-to-sequence architecture typically used for optical character recognition (OCR)…

计算机视觉与模式识别 · 计算机科学 2024-07-29 Jacob Carlson , Tom Bryan , Melissa Dell

The development of LLMs has greatly enhanced the intelligence and fluency of question answering, while the emergence of retrieval enhancement has enabled models to better utilize external information. However, the presence of noise and…

计算与语言 · 计算机科学 2024-09-19 Xingyun Hong , Yan Shao , Zhilin Wang , Manni Duan , Jin Xiongnan

Multimodal Large Language Models (MLLMs) have achieved considerable accuracy in Optical Character Recognition (OCR) from static images. However, their efficacy in video OCR is significantly diminished due to factors such as motion blur,…