20 results for “document encoding”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper presents a methodology for digitizing and encoding the Al-Mawrid Arabic-English dictionary.
This paper compares the preservation of linguistic content in different text encodings (tokens, bytes, pixels) using a shared bottleneck, revealing their distinct strengths in surface form preservatio…
Shihao Rao, Liang Li, Jiapeng Liu, Tong Lin +5 more
The paper introduces DocFormBench, a new benchmark for content-aware document formatting, and proposes DocFormFlow, a workflow that improves formatting accuracy and efficiency by decoupling target loc…
Boyu Niu, Yingjie Xiong, Shurui Li, Linhan Pang +7 more
This paper introduces a benchmark for evaluating document parsing systems that output HTML, which is more suitable for editable and reusable documents.
Minglai Yang, Xinyan Velocity Yu, Pengyuan Li, Xinyu Guo +21 more
The paper introduces Dr. DocBench, a difficulty-aware, comprehensive benchmark designed to rigorously test expert-level and challenging document parsing capabilities for VLMs, demonstrating that curre…
One clear sentence describing what this paper does
This paper systematically analyzes combining dimensionality reduction and quantization to compress text embeddings, showing that this combined approach achieves substantial compression (e.g., 0.1% siz…
This paper introduces Weight Pair Encoding, a method to explicitly finetune neural network weights to admit a smaller grammar.
The paper systematically compares multimodal transformer and LLM approaches for document type classification, finding that specialized multimodal Transformers outperform LLM-based models, especially w…
The paper introduces the Stanford EDGAR Filings Dataset (SEFD), an open-source corpus of financial documents for training and evaluating large language models.
A benchmark of existing tools for reversible pseudonymization and development of a new engine that outperforms them.
The paper analyzes the robustness of current LLM watermarking schemes against various text modifications, concluding that watermarks can be removed with reasonable effort.
This paper investigates the effectiveness of natural-language documentation in helping coding agents resolve software issues.
Establishes conditions for embedding documents as vectors for top-k retrieval and analyzes the required dimension and precision.
One sentence describing what this paper does