157 citations · 167 across the 5 of their papers we have counts for
5 papers
Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking
Tien Nam Nguyen, Emanuela Boros, Ahmed Hamdi +3
Large language models (LLMs) have recently shown promise for historical entity linking, but preference optimization for this task is often formulated with only one negative candida…
Yes but.. Can ChatGPT Identify Entities in Historical Documents?
Carlos-Emiliano González-Gallardo, Emanuela Boros, Nancy Girdhar +3
Large language models (LLMs) have been leveraged for several years now, obtaining state-of-the-art performance in recognizing entities from modern documents. For the last few month…
DocILE Benchmark for Document Information Localization and Extraction
Štěpán Šimsa, Milan Šulc, Michal Uřičář +8
This paper introduces the DocILE benchmark with the largest dataset of business documents for the tasks of Key Information Localization and Extraction and Line Item Recognition. It…
DocILE 2023 Teaser: Document Information Localization and Extraction
Štěpán Šimsa, Milan Šulc, Matyáš Skalický +2
The lack of data for information extraction (IE) from semi-structured business documents is a real problem for the IE community. Publications relying on large-scale datasets use on…
Named Entity Recognition and Classification on Historical Documents: A Survey
Maud Ehrmann, Ahmed Hamdi, Elvys Linhares Pontes +2
After decades of massive digitisation, an unprecedented amount of historical documents is available in digital format, along with their machine-readable texts. While this represent…