Papers by Marcelo Viridiano
Framed Multi30K: A Frame-Based Multimodal-Multilingual Dataset (2024.lrec-main)
Copied to clipboard
Marcelo Viridiano, Arthur Lorenzi, Tiago Timponi Torrent, Ely E. Matos, Adriana S. Pagano, Natália Sathler Sigiliano, Maucha Gamonal, Helen de Andrade Abreu, Lívia Vicente Dutra, Mairon Samagaio, Mariane Carvalho, Franciany Campos, Gabrielly Azalim, Bruna Mazzei, Mateus Fonseca de Oliveira, Ana Carolina Luz, Livia Padua Ruiz, Júlia Bellei, Amanda Pestana, Josiane Costa, Iasmin Rabelo, Anna Beatriz Silva, Raquel Roza, Mariana Souza Mota, Igor Oliveira, Márcio Henrique Pelegrino de Freitas
| Challenge: | Recent advances in image-captioning datasets combine image and language to solve a diverse range of tasks. |
| Approach: | They propose a Brazilian Portuguese multimodal-multilingual dataset that extends the Multi30K dataset with 158,915 original Brazilian Portuguese descriptions and 30,104 Brazilian Portuguese translations. |
| Outcome: | The proposed dataset adds 2,677,613 frame evocation labels to the 158,915 English descriptions and to the ones created for Brazilian Portuguese. |
SHADES: Towards a Multilingual Assessment of Stereotypes in Large Language Models (2025.naacl-long)
Copied to clipboard
Margaret Mitchell, Giuseppe Attanasio, Ioana Baldini, Miruna Clinciu, Jordan Clive, Pieter Delobelle, Manan Dey, Sil Hamilton, Timm Dill, Jad Doughman, Ritam Dutt, Avijit Ghosh, Jessica Zosa Forde, Carolin Holtermann, Lucie-Aimée Kaffee, Tanmay Laud, Anne Lauscher, Roberto L Lopez-Davila, Maraim Masoud, Nikita Nangia, Anaelia Ovalle, Giada Pistilli, Dragomir Radev, Beatrice Savoldi, Vipul Raheja, Jeremy Qin, Esther Ploeger, Arjun Subramonian, Kaustubh Dhole, Kaiser Sun, Amirbek Djanibekov, Jonibek Mansurov, Kayo Yin, Emilio Villa Cueva, Sagnik Mukherjee, Jerry Huang, Xudong Shen, Jay Gala, Hamdan Al-Ali, null Tair Djanibekov, Nurdaulet Mukhituly, Shangrui Nie, Shanya Sharma, Karolina Stanczak, Eliza Szczechla, Tiago Timponi Torrent, Deepak Tunuguntla, Marcelo Viridiano, Oskar Van Der Wal, Adina Yakefu, Aurélie Névéol, Mike Zhang, Sydney Zink, Zeerak Talat
| Challenge: | Large Language Models reproduce and exacerbate social biases present in training data, and resources to quantify this issue are limited. |
| Approach: | They propose a multilingual parallel dataset to examine culturally-specific stereotypes that may be learned by LLMs. |
| Outcome: | The proposed dataset includes stereotypes from 20 regions around the world and 16 languages, spanning multiple identity categories subject to discrimination worldwide. |