Evaluation of AI ethics tools in language models: a developers' perspective case study.

Helena Almeida Maia Helena de Almeida Maia https://orcid.org/0000-0002-8253-9004

Jhessica Silva Diego A. B. Moreira Gabriel Oliveira dos Santos Alef I. Ferreira Helena Almeida Maia Sandra Avila Hélio Pedrini Evaluation of AI ethics tools in language models: a developers' perspective case study. 2026 April 210 6 AI Ethics 2 https://doi.org/10.1007/s43681-025-00914-2 db/journals/aiethics/aiethics6.html#SilvaMSFMAP26 streams/journals/aiethics

Marcos Roberto e Souza Helena de Almeida Maia Hélio Pedrini NAFT and SynthStab: A RAFT-Based Network and a Synthetic Dataset for Digital Video Stabilization. 2345-2370 2025 May 133 Int. J. Comput. Vis. 5 https://doi.org/10.1007/s11263-024-02264-8 db/journals/ijcv/ijcv133.html#SouzaMP25 streams/journals/ijcv

Gustavo Bonil João Medrado Gondim Viviane Bonadia dos Santos Simone Tiemi Hashiguti Helena Almeida Maia Nádia Félix F. da Silva Hélio Pedrini Sandra Avila Clustering Discourses: Racial Biases in Short Stories about Women Generated by Large Language Models. 66-77 2025 STIL https://doi.org/10.5753/stil.2025.37814 conf/stil/2025 db/conf/stil/stil2025.html#BonilGSHMSPA25

Gustavo Bonil Simone Tiemi Hashiguti Jhessica Silva João Medrado Gondim Helena Almeida Maia Nádia Félix F. da Silva Hélio Pedrini Sandra Avila Yet another algorithmic bias: A Discursive Analysis of Large Language Models Reinforcing Dominant Discourses on Gender and Race. 2025 August abs/2508.10304 CoRR https://doi.org/10.48550/arXiv.2508.10304 db/journals/corr/corr2508.html#abs-2508-10304 streams/journals/corr

Gustavo Bonil João Medrado Gondim Viviane M. Bonadia dos Santos Simone Tiemi Hashiguti Helena Almeida Maia Nádia Félix F. da Silva Hélio Pedrini Sandra Avila Clustering Discourses: Racial Biases in Short Stories about Women Generated by Large Language Models. 2025 September abs/2509.02834 CoRR https://doi.org/10.48550/arXiv.2509.02834 db/journals/corr/corr2509.html#abs-2509-02834 streams/journals/corr

George Corrêa de Araújo Helena de Almeida Maia Hélio Pedrini A Framework for Generating Artificial Datasets to Validate Absolute and Relative Position Concepts. 2025 September abs/2509.18177 CoRR https://doi.org/10.48550/arXiv.2509.18177 db/journals/corr/corr2509.html#abs-2509-18177 streams/journals/corr

Diego A. B. Moreira Alef I. Ferreira Jhessica Silva Gabriel Oliveira dos Santos Gustavo Bonil João Medrado Gondim Viviane Bonadia dos Santos Helena Almeida Maia Simone Tiemi Hashiguti Nádia Félix F. da Silva Carolina Scarton Hélio Pedrini Sandra Avila CACARA: Cross-Modal Alignment Leveraging a Text-Centric Approach for Cost-Effective Multimodal and Multilingual Learning. 2025 December abs/2512.00496 CoRR https://doi.org/10.48550/arXiv.2512.00496 db/journals/corr/corr2512.html#abs-2512-00496 streams/journals/corr

Jhessica Silva Diego A. B. Moreira Gabriel Oliveira dos Santos Alef I. Ferreira Helena Almeida Maia Sandra de Avila Hélio Pedrini Evaluation of AI Ethics Tools in Language Models: A Developers' Perspective Case Stud. 2025 December abs/2512.15791 CoRR https://doi.org/10.48550/arXiv.2512.15791 db/journals/corr/corr2512.html#abs-2512-15791 streams/journals/corr

Diego A. B. Moreira Alef Iury Siqueira Ferreira Jhessica Silva Gabriel Oliveira dos Santos Luiz Pereira João Medrado Gondim Gustavo Bonil Helena Almeida Maia Nádia Félix F. da Silva Simone Tiemi Hashiguti Jefersson A. dos Santos Hélio Pedrini Sandra Avila FairPIVARA: Reducing and Assessing Biases in CLIP-Based Multimodal Models. 2024 BMVC Workshops https://bmva-archive.org.uk/bmvc/2024/workshops/PFATCV/11_FairPIVARA_Reducing_and_Ass.pdf conf/bmvc/2024w db/conf/bmvc/bmvc2024w.html#MoreiraFSSPGBMS24 Luis Gustavo Lorgus Decker Jose Luis Flores-Campana Marcos Roberto e Souza Helena de Almeida Maia Hélio Pedrini Zero-Shot Synth-to-Real Depth Estimation: From Synthetic Street Scenes to Real-World Data. 1-6 2024 SIBGRAPI https://doi.org/10.1109/SIBGRAPI62404.2024.10716265 conf/sibgrapi/2024 db/conf/sibgrapi/sibgrapi2024.html#DeckerFSMP24 Jose Luis Flores-Campana Luis Gustavo Lorgus Decker Marcos Roberto e Souza Helena de Almeida Maia Hélio Pedrini Image Inpainting on the Sketch-Pencil Domain with Vision Transformers. 122-132 2024 VISIGRAPP (3): VISAPP https://doi.org/10.5220/0012363500003660 conf/visigrapp/2024-3 db/conf/visigrapp/visigrapp2024-3.html#Flores-CampanaD24

Diego A. B. Moreira Alef Iury Siqueira Ferreira Gabriel Oliveira dos Santos Luiz Pereira João Medrado Gondim Gustavo Bonil Helena de Almeida Maia Nádia Félix F. da Silva Simone Tiemi Hashiguti Jefersson A. dos Santos Hélio Pedrini Sandra Avila FairPIVARA: Reducing and Assessing Biases in CLIP-Based Multimodal Models. 2024 abs/2409.19474 CoRR https://doi.org/10.48550/arXiv.2409.19474 db/journals/corr/corr2409.html#abs-2409-19474 streams/journals/corr

Jose Luis Flores-Campana Luis Gustavo Lorgus Decker Marcos Roberto e Souza Helena de Almeida Maia Hélio Pedrini Variable-hyperparameter visual transformer for efficient image inpainting. 57-68 2023 June 113 Comput. Graph. https://doi.org/10.1016/j.cag.2023.05.006 db/journals/cg/cg113.html#FloresCampanaDSMP23

Marcos Roberto e Souza Helena de Almeida Maia Hélio Pedrini Survey on Digital Video Stabilization: Concepts, Methods, and Challenges. 47:1-47:37 2023 55 ACM Comput. Surv. 3 https://doi.org/10.1145/3494525 db/journals/csur/csur55.html#SouzaMP23

Marcos Roberto e Souza Helena de Almeida Maia Hélio Pedrini Rethinking two-dimensional camera motion estimation assessment for digital video stabilization: A camera motion field-based metric. 126768 2023 November 559 Neurocomputing https://doi.org/10.1016/j.neucom.2023.126768 db/journals/ijon/ijon559.html#SouzaMP23

Artur Jordão George Corrêa de Araújo Helena de Almeida Maia Hélio Pedrini When Layers Play the Lottery, all Tickets Win at Initialization. 1196-1205 2023 ICCV (Workshops) https://doi.org/10.1109/ICCVW60793.2023.00130 conf/iccvw/2023 db/conf/iccvw/iccvw2023.html#JordaoAMP23

Artur Jordão George Corrêa de Araújo Helena de Almeida Maia Hélio Pedrini When Layers Play the Lottery, all Tickets Win at Initialization. 2023 abs/2301.10835 CoRR https://doi.org/10.48550/arXiv.2301.10835 db/journals/corr/corr2301.html#abs-2301-10835

Gabriel Oliveira dos Santos Diego A. B. Moreira Alef Iury Siqueira Ferreira Jhessica Silva Luiz Pereira Pedro Bueno Thiago Sousa Helena Almeida Maia Nádia Félix F. da Silva Esther Colombini Hélio Pedrini Sandra Avila CAPIVARA: Cost-Efficient Approach for Improving Multilingual CLIP Performance on Low-Resource Languages. 2023 abs/2310.13683 CoRR https://doi.org/10.48550/arXiv.2310.13683 db/journals/corr/corr2310.html#abs-2310-13683

Marcos Roberto e Souza Helena de Almeida Maia Anderson Carlos Sousa e Santos Marcelo Bernardes Vieira Hélio Pedrini Multi-Script Video Caption Localization Based on Visual Rhythms. 2022 36 Appl. Artif. Intell. 1 https://doi.org/10.1080/08839514.2022.2032926 https://www.wikidata.org/entity/Q114010894 db/journals/aai/aai36.html#SouzaMSVP22

Edson R. Bollis Helena Almeida Maia Hélio Pedrini Sandra Avila Weakly supervised attention-based models using activation maps for citrus mite and insect pest classification. 106839 2022 195 Comput. Electron. Agric. https://doi.org/10.1016/j.compag.2022.106839 db/journals/cea/cea195.html#BollisMPA22

Jose Luis Flores-Campana Luis Gustavo Lorgus Decker Marcos Roberto e Souza Helena de Almeida Maia Hélio Pedrini Multi-Scale Patch Partitioning for Image Inpainting Based on Visual Transformers. 180-185 2022 SIBGRAPI https://doi.org/10.1109/SIBGRAPI55357.2022.9991754 conf/sibgrapi/2022 db/conf/sibgrapi/sibgrapi2022.html#Flores-CampanaD22

André de Souza Brito Marcelo Bernardes Vieira Saulo Moraes Villela Hemerson Tacon Hugo de Lima Chaves Helena de Almeida Maia Darwin Ttito Concha Hélio Pedrini Weighted voting of multi-stream convolutional neural networks for video-based action recognition using optical flow rhythms. 103112 2021 77 J. Vis. Commun. Image Represent. https://doi.org/10.1016/j.jvcir.2021.103112 https://www.wikidata.org/entity/Q114013752 db/journals/jvcir/jvcir77.html#BritoVVTCMCP21

Marcos Roberto e Souza Jhonatas S. Conceição Jose L. Flores-Campana Luis G. L. Decker Diogo C. Luvizon Gustavo Sutter P. Carvalho Helena Almeida Maia Hélio Pedrini Pyramidal Layered Scene Inference with Image Outpainting for Monocular View Synthesis. 37-46 2021 CAIP (1) https://doi.org/10.1007/978-3-030-89128-2_4 conf/caip/2021-1 db/conf/caip/caip2021-1.html#SouzaCFDLCMP21

Edson R. Bollis Helena Almeida Maia Hélio Pedrini Sandra Avila Weakly Supervised Attention-based Models Using Activation Maps for Citrus Mite and Insect Pest Classification. 2021 abs/2110.00881 CoRR https://arxiv.org/abs/2110.00881 db/journals/corr/corr2110.html#abs-2110-00881

Helena de Almeida Maia Visual rhythm-based convolutional neural networks and adaptive fusion for a multi-stream architecture applied to human action recognition : Redes neurais convolucionais baseadas em ritmos visuais e fusão adaptativa para uma arquitetura de múltiplos canais aplicada ao reconhecimento de ações humanas University of Campinas, Brazil 2020 LaReferencia (lareferencia.info): oai::1157496 https://hdl.handle.net/20.500.12733/1640023

Marcos Roberto e Souza Helena de Almeida Maia Marcelo Bernardes Vieira Hélio Pedrini Survey on visual rhythms: A spatio-temporal representation for video sequences. 409-422 2020 402 Neurocomputing https://doi.org/10.1016/j.neucom.2020.04.035 db/journals/ijon/ijon402.html#SouzaMVP20

Helena de Almeida Maia Marcos Roberto e Souza Anderson Carlos Sousa e Santos Julio Cesar Mendoza Bobadilla Marcelo Bernardes Vieira Hélio Pedrini Early Stopping for Two-Stream Fusion Applied to Action Recognition. 319-333 2020 VISIGRAPP (Revised Selected Papers) https://doi.org/10.1007/978-3-030-94893-1_14 conf/grapp/2020s db/conf/grapp/selection2020.html#MaiaSSBVP20 Anderson Carlos Sousa e Santos Helena de Almeida Maia Marcos Roberto e Souza Marcelo Bernardes Vieira Hélio Pedrini Fuzzy Fusion for Two-stream Action Recognition. 117-123 2020 VISIGRAPP (5: VISAPP) https://doi.org/10.5220/0008973901170123 conf/visapp/2020-2 db/conf/visapp/visapp2020-2.html#SantosMSVP20 Hemerson Tacon André de Souza Brito Hugo de Lima Chaves Marcelo Bernardes Vieira Saulo Moraes Villela Helena de Almeida Maia Darwin Ttito Concha Hélio Pedrini Multi-stream Architecture with Symmetric Extended Visual Rhythms for Deep Learning Human Action Recognition. 351-358 2020 VISIGRAPP (5: VISAPP) https://doi.org/10.5220/0008958003510358 conf/visapp/2020-2 db/conf/visapp/visapp2020-2.html#TaconBCVVMCP20 Hugo de Lima Chaves Kevyn Swhants Ribeiro André de Souza Brito Hemerson Tacon Marcelo Bernardes Vieira Augusto Santiago Cerqueira Saulo Moraes Villela Helena de Almeida Maia Darwin Ttito Concha Hélio Pedrini Filter Learning from Deep Descriptors of a Fully Convolutional Siamese Network for Tracking in Videos. 685-694 2020 VISIGRAPP (4: VISAPP) https://doi.org/10.5220/0008957606850694 conf/visapp/2020-1 db/conf/visapp/visapp2020-1.html#ChavesRBTVCVMCP20 Hemerson Tacon André de Souza Brito Hugo de Lima Chaves Marcelo Bernardes Vieira Saulo Moraes Villela Helena de Almeida Maia Darwin Ttito Concha Hélio Pedrini Human Action Recognition Using Convolutional Neural Networks with Symmetric Time Extension of Visual Rhythms. 351-366 2019 ICCSA (1) https://doi.org/10.1007/978-3-030-24289-3_26 conf/iccsa/2019-1 db/conf/iccsa/iccsa2019-1.html#TaconBCVVMCP19 Helena Almeida Maia Marcos Roberto e Souza Anderson Santos 0001 Hélio Pedrini Hemerson Tacon André de Souza Brito Hugo de Lima Chaves Marcelo Bernardes Vieira Saulo Moraes Villela Learnable Visual Rhythms Based on the Stacking of Convolutional Neural Networks for Action Recognition. 1794-1799 2019 ICMLA https://doi.org/10.1109/ICMLA.2019.00290 conf/icmla/2019 db/conf/icmla/icmla2019.html#MaiaSSPTBCVV19 Darwin Ttito Concha Helena de Almeida Maia Hélio Pedrini Hemerson Tacon André de Souza Brito Hugo de Lima Chaves Marcelo Bernardes Vieira Multi-stream Convolutional Neural Networks for Action Recognition in Video Sequences Based on Adaptive Visual Rhythms. 473-480 2018 ICMLA https://doi.org/10.1109/ICMLA.2018.00077 conf/icmla/2018 db/conf/icmla/icmla2018.html#ConchaMPTBCV18 Helena de Almeida Maia Fabio Luiz Marinho De Oliveira Marcelo Bernardes Vieira Independent selection and validation for tracking-learning-detection. 3469-3473 2016 ICIP https://doi.org/10.1109/ICIP.2016.7533004 conf/icip/2016 db/conf/icip/icip2016.html#MaiaOV16

Helena Almeida Maia Ana Mara De Oliveira Figueiredo Fabio Luiz Marinho De Oliveira Virgínia Fernandes Mota Marcelo Bernardes Vieira A Video Tensor Self-descriptor Based on Block Matching. 90-102 2015 11 J. Mobile Multimedia 1&2 http://www.rintonpress.com/xjmm11/jmm-11-12/090-102.pdf db/journals/jmm/jmm11.html#MaiaFOMV15

Ana Mara De Oliveira Figueiredo Helena Almeida Maia Fabio Luiz Marinho De Oliveira Virgínia Fernandes Mota Marcelo Bernardes Vieira A Video Tensor Self-descriptor Based on Block Matching. 401-414 2014 ICCSA (6) https://doi.org/10.1007/978-3-319-09153-2_30 conf/iccsa/2014-6 db/conf/iccsa/iccsa2014-6.html#FigueiredoMOMV14 George Corrêa de Araújo Sandra Eliza Fontes de AvilaSandra de AvilaSandra Avila Edson BollisEdson R. Bollis Gustavo Bonil André de Souza Brito Pedro Bueno Augusto Santiago Cerqueira Hugo de Lima Chaves Esther Luna ColombiniEsther Colombini Jhonatas Santos de Jesus ConceiçãoJhonatas S. Conceição Darwin Ttito Concha Luis G. L. DeckerLuis Gustavo Lorgus Decker Alef I. Ferreira Alef Iury Siqueira Ferreira Ana Mara De Oliveira Figueiredo Jose L. Flores-CampanaJose Luis Flores-Campana João Medrado Gondim Simone Tiemi Hashiguti Artur Jordão Diogo C. Luvizon Julio Mendoza 0001Julio Cesar Mendoza Bobadilla Diego A. B. Moreira Virgínia Fernandes Mota Fabio Luiz Marinho De Oliveira Hélio Pedrini Luiz Pereira Kevyn Swhants Ribeiro Anderson Carlos Sousa e SantosAnderson Santos 0001 Gabriel Oliveira dos Santos Jefersson A. dos Santos Viviane Bonadia dos SantosViviane M. Bonadia dos Santos Carolina Scarton Jhessica Silva Nádia Félix F. da Silva Thiago Sousa Marcos Roberto e Souza Gustavo Sutter 0002Gustavo Sutter P. Carvalho Hemerson Tacon Marcelo Bernardes Vieira Saulo Moraes Villela