Related papers: Deciphering the Underserved: Benchmarking LLM OCR …

Extremely low-resource languages, especially those written in rare scripts, as shown in Figure 1, remain largely unsupported by large language models (LLMs). This is due in part to compounding factors such as the lack of training data. This…

Large models have recently played a dominant role in natural language processing and multimodal vision-language learning. However, their effectiveness in text-related visual tasks remains relatively unexplored. In this paper, we conducted a…

This research paper introduces a novel word-level Optical Character Recognition (OCR) model specifically designed for digital Urdu text, leveraging transformer-based architectures and attention mechanisms to address the distinct challenges…

There has been recent interest in improving optical character recognition (OCR) for endangered languages, particularly because a large number of documents and books in these languages are not in machine-readable formats. The performance of…

With the growing adoption of Retrieval-Augmented Generation (RAG) in document processing, robust text recognition has become increasingly critical for knowledge extraction. While OCR (Optical Character Recognition) for English and other…

How can large language models (LLMs) process and translate endangered languages? Many languages lack a large corpus to train a decent LLM; therefore existing LLMs rarely perform well in unseen, endangered languages. On the contrary, we…

Multimodal Large Language Models (MLLMs) enhance the potential of natural language processing. However, their actual impact on document information extraction remains unclear. In particular, it is unclear whether an MLLM-only…

Large language models (LLMs) have achieved impressive results in high-resource languages like English, yet their effectiveness in low-resource and morphologically rich languages remains underexplored. In this paper, we present a…

Transliteration, the process of mapping text from one script to another, plays a crucial role in multilingual natural language processing, especially within linguistically diverse contexts such as India. Despite significant advancements…

Arabic document OCR remains a challenging task due to the language's cursive script, diverse fonts, diacritics, and right-to-left orientation. While modern Multimodal Large Language Models (MLLMs) have advanced document understanding for…

Optical Character Recognition (OCR) plays a crucial role in digitizing historical and multilingual documents, yet OCR errors - imperfect extraction of text, including character insertion, deletion, and substitution can significantly impact…

Vision-language models (VLMs) can read text from images, but where does this optical character recognition (OCR) information enter the language processing stream? We investigate the OCR routing mechanism across three architecture families…

E-commerce platforms require structured product data in the form of attribute-value pairs to offer features such as faceted product search or attribute-based product comparison. However, vendors often provide unstructured product…

Many studies on (Offline) Handwritten Text Recognition (HTR) systems have focused on building state-of-the-art models for line recognition on small corpora. However, adding HTR capability to a large scale multilingual OCR system poses new…

Objective Structured Clinical Examinations (OSCEs) are widely used to assess medical students' communication skills, but scoring interview-based assessments is time-consuming and potentially subject to human bias. This study explored the…

Large language models (LLMs) have garnered significant interest in natural language processing (NLP), particularly their remarkable performance in various downstream tasks in resource-rich languages. Recent studies have highlighted the…

Optical Character Recognition (OCR) for low-resource languages remains a significant challenge due to the scarcity of large-scale annotated training datasets. Languages such as Kashmiri, with approximately 7 million speakers and a complex…

Large Language Models (LLMs) are increasingly explored for educational tasks such as grading, yet their alignment with human evaluation in real classrooms remains underexamined. In this study, we investigate the feasibility of using an LLM…

We explore the capabilities of LVLMs and LLMs in deciphering rare scripts not encoded in Unicode. We introduce a novel approach to construct a multimodal dataset of linguistic puzzles involving such scripts, utilizing a tokenization method…

This paper presents a study on the feasibility of using large language models (LLM) for coding with low-resource and domain-specific programming languages that typically lack the amount of data required for effective LLM processing…