emanuelaboros (Emanuela Boros)

updated a dataset 2 days ago

emanuelaboros/Hist-Pile-NER-Type

Viewer • Updated 2 days ago • 9.48k • 174 • 1

updated a model 5 days ago

emanuelaboros/chrono-link-bert-americanstories-1850-1890

Fill-Mask • 0.1B • Updated 5 days ago • 25

commented on Can LLMs Correct Historical OCR Without Rewriting History? 5 days ago

Hello @stefan-it , glad to see your comment. I'm curious, the impact levels, are relative to what/whom? How could we/one automate such labelling?

published an article 5 days ago

Article

Can LLMs Correct Historical OCR Without Rewriting History?

emanuelaboros

•

5 days ago

• 2

upvoted a collection 5 days ago

DAI-CReTDHI project

Collection

Models & datasets related to the DAI-CReTDHI project: https://dai-cretdhi.univ-lr.fr/ • 8 items • Updated May 6 • 1

authored 2 papers 5 days ago

Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking

Paper • 2609.07379 • Published Sep 10 • 1

When Superpixels Fail on Documents: A Study of Segmentation for LIME Explanations

Paper • 2609.07462 • Published Sep 7

updated a collection 5 days ago

General

Collection

1 item • Updated 5 days ago

upvoted a collection 5 days ago

Old French datasets

Collection

6 items • Updated Jun 22 • 1

published a dataset 6 days ago

emanuelaboros/Hist-Pile-NER-Type

Viewer • Updated 2 days ago • 9.48k • 174 • 1

authored 2 papers 11 days ago

ICDAR 2026 HIPE-OCRepair Competition on LLM-Assisted OCR Post-Correction for Historical Documents

Paper • 2607.08143 • Published Jul 9

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

Paper • 2509.14233 • Published Sep 17, 2025 • 25

liked a dataset 17 days ago

biglam/europeana_newspapers

Viewer • Updated 18 days ago • 17.8M • 1.27k • 68

updated a Space 19 days ago

README

🔬

L3i research models, datasets, and demos

updated a Space 3 months ago

NLP Conference Tracker

📅

published 2 Spaces 3 months ago

NLP Conference Tracker

📅

README

🔬

L3i research models, datasets, and demos

updated a model 3 months ago

emanuelaboros/historical-ner-baseline

Token Classification • 0.1B • Updated Jul 16 • 18

upvoted a collection 3 months ago

mechanistic interpretability with sparse autoencoders

Collection

A collection of papers that I found useful for learning about using Sparse Autoencoders for finding interpretable features in language models • 9 items • Updated Sep 3, 2024 • 4

liked a model 3 months ago

manelalab/chrono-bert-v1-20181231

Fill-Mask • 0.1B • Updated Jun 10, 2025 • 2.51k • 4

Emanuela Boros PRO

AI & ML interests

Recent Activity

Organizations

emanuelaboros/Hist-Pile-NER-Type

emanuelaboros/chrono-link-bert-americanstories-1850-1890

Can LLMs Correct Historical OCR Without Rewriting History?

DAI-CReTDHI project

Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking

When Superpixels Fail on Documents: A Study of Segmentation for LIME Explanations

General

Old French datasets

emanuelaboros/Hist-Pile-NER-Type

ICDAR 2026 HIPE-OCRepair Competition on LLM-Assisted OCR Post-Correction for Historical Documents

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

biglam/europeana_newspapers

README

NLP Conference Tracker

NLP Conference Tracker

README

emanuelaboros/historical-ner-baseline

mechanistic interpretability with sparse autoencoders

manelalab/chrono-bert-v1-20181231

Emanuela Boros PRO

AI & ML interests

Recent Activity

Organizations

emanuelaboros's activity

Can LLMs Correct Historical OCR Without Rewriting History?

README

NLP Conference Tracker

NLP Conference Tracker

README