Posts by Collection

LeNER-Br: A Dataset for Named Entity Recognition in Brazilian Legal Text

Published in Computational Processing of the Portuguese Language - 13th International Conference, PROPOR 2018, Canela, Brazil, September 24-26, 2018, Proceedings, 2018

Access paper here

Recommended citation: Pedro {Luz de Araujo}, Te{\'{o}}filo Campos, Renato Oliveira, Matheus Stauffer, Samuel Couto, Paulo Bermejo, "LeNER-Br: A Dataset for Named Entity Recognition in Brazilian Legal Text." Computational Processing of the Portuguese Language - 13th International Conference, PROPOR 2018, Canela, Brazil, September 24-26, 2018, Proceedings, 2018.
Download Paper

Inferring the Source of Official Texts: Can SVM Beat ULMFiT?

Published in Computational Processing of the Portuguese Language - 14th International Conference, PROPOR 2020, Evora, Portugal, March 2-4, 2020, Proceedings, 2020

Access paper here

Recommended citation: Pedro {Luz de Araujo}, Te{\'{o}}filo Campos, Marcelo Sousa, "Inferring the Source of Official Texts: Can SVM Beat ULMFiT?." Computational Processing of the Portuguese Language - 14th International Conference, PROPOR 2020, Evora, Portugal, March 2-4, 2020, Proceedings, 2020.
Download Paper

Topic Modelling Brazilian Supreme Court Lawsuits

Published in Legal Knowledge and Information Systems - JURIX 2020: The Thirty-third Annual Conference, Brno, Czech Republic, December 9-11, 2020, 2020

Access paper here

Recommended citation: Pedro {Luz de Araujo}, Te{\'{o}}filo Campos, "Topic Modelling Brazilian Supreme Court Lawsuits." Legal Knowledge and Information Systems - JURIX 2020: The Thirty-third Annual Conference, Brno, Czech Republic, December 9-11, 2020, 2020.
Download Paper

VICTOR: a Dataset for Brazilian Legal Documents Classification

Published in Proceedings of The 12th Language Resources and Evaluation Conference, LREC 2020, Marseille, France, May 11-16, 2020, 2020

Access paper here

Recommended citation: Pedro {Luz de Araujo}, Te{\'{o}}filo Campos, Fabricio Braz, Nilton Silva, "VICTOR: a Dataset for Brazilian Legal Documents Classification." Proceedings of The 12th Language Resources and Evaluation Conference, LREC 2020, Marseille, France, May 11-16, 2020, 2020.
Download Paper

Checking HateCheck: A Cross-Functional Analysis of Behaviour-Aware Learning for Hate Speech Detection

Published in Proceedings of NLP Power! The First Workshop on Efficient Benchmarking in NLP, 2022

Use Google Scholar for full citation

Recommended citation: Pedro {Luz de Araujo}, Benjamin Roth, "Checking HateCheck: A Cross-Functional Analysis of Behaviour-Aware Learning for Hate Speech Detection." Proceedings of NLP Power! The First Workshop on Efficient Benchmarking in NLP, 2022.

Cross-functional Analysis of Generalization in Behavioral Learning

Published in Trans. Assoc. Comput. Linguistics, 2023

Access paper here

Recommended citation: Pedro {Luz de Araujo}, Benjamin Roth, "Cross-functional Analysis of Generalization in Behavioral Learning." Trans. Assoc. Comput. Linguistics, 2023.
Download Paper

Sequence-aware multimodal page classification of Brazilian legal documents

Published in Int. J. Document Anal. Recognit., 2023

Access paper here

Recommended citation: Pedro {Luz de Araujo}, Ana Almeida, Fabricio Braz, Nilton Silva, Flavio Barros, Te{\'{o}}filo Campos, "Sequence-aware multimodal page classification of Brazilian legal documents." Int. J. Document Anal. Recognit., 2023.
Download Paper

Exploring prompts to elicit memorization in masked language model-based named entity recognition

Published in CoRR, 2024

Access paper here

Recommended citation: Yuxi Xia, Anastasiia Sedova, Pedro {Luz de Araujo}, Vasiliki Kougia, Lisa Nu{\ss}baumer, Benjamin Roth, "Exploring prompts to elicit memorization in masked language model-based named entity recognition." CoRR, 2024.
Download Paper

Paper Title Number 4

Published in GitHub Journal of Bugs, 2024

This paper is about fixing template issue #693.

Recommended citation: Your Name, You. (2024). "Paper Title Number 3." GitHub Journal of Bugs. 1(3).
Download Paper

Paper Title Number 5, with math \(E=mc^2\)

Published in GitHub Journal of Bugs, 2024

This paper is about a famous math equation, \(E=mc^2\)

Recommended citation: Your Name, You. (2024). "Paper Title Number 3." GitHub Journal of Bugs. 1(3).
Download Paper

Text-Guided Alternative Image Clustering

Published in Proceedings of the 9th Workshop on Representation Learning for NLP (RepL4NLP-2024), 2024

Access paper here

Recommended citation: Andreas Stephan, Lukas Miklautz, Collin Leiber, Pedro Luz, Dominik R{\'e}p{\'a}s, Claudia Plant, Benjamin Roth, "Text-Guided Alternative Image Clustering." Proceedings of the 9th Workshop on Representation Learning for NLP (RepL4NLP-2024), 2024.
Download Paper

Functionality Learning through Specification Instructions

Published in Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

Use Google Scholar for full citation

Recommended citation: Pedro Luz, Benjamin Roth, "Functionality Learning through Specification Instructions." Findings of the Association for Computational Linguistics: EMNLP 2024, 2024.

Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles

Published in arXiv, 2025

Accepted at ACL 2025.

Recommended citation: Yuxi Xia, Pedro {Luz de Araujo}, Klim Zaporojets, Benjamin Roth, "Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles." arXiv, 2025.
Download Paper

Specification overfitting in artificial intelligence

Published in Artif. Intell. Rev., 2025

Access paper here

Recommended citation: Benjamin Roth, Pedro {Luz de Araujo}, Yuxi Xia, Saskia Kaltenbrunner, Christoph Korab, "Specification overfitting in artificial intelligence." Artif. Intell. Rev., 2025.
Download Paper

Helpful Assistant or Fruitful Facilitator? Investigating How Personas Affect Language Model Behavior

Published in PLOS ONE, 2025

Use Google Scholar for full citation

Recommended citation: Pedro {Luz de Araujo}, Benjamin Roth, "Helpful Assistant or Fruitful Facilitator? Investigating How Personas Affect Language Model Behavior." PLOS ONE, 2025.

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.