Fetching the paper…
Reading the bibliography…
Business Document Information Extraction (BDIE) is the problem of transforming a blob of unstructured information (raw text, scanned documents, etc.) into a structured format that downstream systems can parse and use.
“RoBERTa: A Robustly Optimized BERT Pretraining Approach”, 2019
Yinhan Liu et al · 1907
Earlier work this paper cites.
“Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks”, 2021
Patrick Lewis et al · 2005
Earlier work this paper cites.
“A robust image hashing based on discrete wavelet transform”
Satendra Singh and Gaurav Bhatnagar · 2017
Earlier work this paper cites.
“End-to-End Object Detection with Transformers”
Nicolas Carion et al · 2020
Earlier work this paper cites.
“LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking”
Yupan Huang, Tengchao Lv, Lei Cui, Yutong Lu and Furu Wei · 2022
Earlier work this paper cites.
“Business Document Information Extraction: Towards Practical Benchmarks”, 2023
Matyáš Skalický, Štěpán Šimsa, Michal Uřičář and Milan Šulc · 2023
Earlier work this paper cites.
“GriTS: Grid table similarity metric for table structure recognition”, 2023
Brandon Smock, Rohith Pesala and Robin Abraham · 2023
Cited alongside, same era.
“Efficient Guided Generation for Large Language Models”, 2023
Brandon. Willard and Rémi Louf · 2023
Cited alongside, same era.
“Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering”, 2023
Wenjin Wang, Yunhao Li, Yixin Ou and Yin Zhang · 2023
Cited alongside, same era.
“GPT-3.5 Documentation” https://platform.openai.com/docs/models/gpt-3-5-turbo [Accessed: 2024-03-08], 2023
OpenAI · 2023
Cited alongside, same era.
“DocILE Benchmark for Document Information Localization and Extraction”, 2023
“Overview of DocILE 2023: Document Information Localization and Extraction”
Štěpán Šimsa et al · 2023
Later among the works it cites.
“Table detection for visually rich document images”
Bin Xiao, Murat Simsek, Burak Kantarci and Ala Alkheir · 2023
Later among the works it cites.
“Hermes 2 Pro - Mistral 7B” https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B [Accessed: 2024-03-08], 2024
interstellarninja, Teknium, theemozilla, karan4d and huemin · 2024
Closest in time.
“LoRAX + Outlines: Better JSON Extraction with Structured Generation and LoRA” https://predibase.com/blog/lorax-outlines-better-json-extraction-with-structured-generation-and-lora [Accessed: 2024-03-08], 2024
Jeffrey Tang and Travis Addair · 2024
Closest in time.
“ANLS* – A Universal Document Processing Metric for Generative Large Language Models”, 2024
David Peer, Philemon Schöpf, Volckmar Nebendahl, Alexander Rietzler and Sebastian Stabinger · 2024
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Štěpán Šimsa et al · 2023
Cited alongside, same era.
“QLoRA: Efficient Finetuning of Quantized LLMs”, 2023
Tim Dettmers, Artidoro Pagnoni, Ari Holtzman and Luke Zettlemoyer · 2023
Cited alongside, same era.
Closest in time.
“Axolotl” https://openaccess-ai-collective.github.io/axolotl/ [Accessed: 2024-03-08], 2024
Open Collective · 2024
Closest in time.