Fairness in Language Models: Equally right for the right reasons

Informations projet

FairER

N° de convention de subvention: 101065558

DOI

10.3030/101065558

Projet clôturé

Date de signature de la CE 16 Juin 2022

Date de début 1 Septembre 2022

Date de fin 31 Août 2024

Financé au titre de

• Marie Skłodowska-Curie Actions (MSCA)

Coût total

Aucune donnée

Contribution de l’UE

€ 214 934,40

Coordonné par

KOBENHAVNS UNIVERSITET
Denmark

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Livrables

Data Management Plan (1)

Data Management Plan

The Data Management Plan describes the data management life cyclefor all data sets that will be collected processed or generated by the action It is adocument describing what data will be collected processed or generated andfollowing what methodology and standards whether and how this data will beshared andor made open and how it will be curated and preserved

Documents, reports (1)

Communication, Dissemination & Outreach Plan

The plan describes the planned measures to maximize the impact ofthe project, including the dissemination and exploitation measures that are planned,and the target group(s) addressed. Regarding communication measures and publicengagement strategy, the aim is to inform and reach out to society and show theactivities performed, and the use and the benefits the project will have for citizens.

Publications

Conference proceedings (6)

Evaluating Webcam-based Gaze Data as an Alternative for Human Rationale Annotations

Auteurs: Stephanie Brandl, Oliver Eberle, Tiago Ribeiro, Anders Søgaard, Nora Hollenstein
Publié dans: 2024
Éditeur: ELRA and ICCL

Every word counts: A multilingual analysis of individual human alignment with model attention

Auteurs: Stephanie Brandl and Nora Hollenstein
Publié dans: 2022
Éditeur: Association for Computational Linguistics

Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models

Auteurs: Laura Cabello, Emanuele Bugliarello, Stephanie Brandl, Desmond Elliott
Publié dans: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2023.emnlp-main.525

On the Interplay between Fairness and Explainability

Auteurs: Stephanie Brandl, Emanuele Bugliarello, Ilias Chalkidis
Publié dans: Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024), 2024
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2024.trustnlp-1.10

Rather a Nurse than a Physician - Contrastive Explanations under Investigation

Auteurs: Oliver Eberle, Ilias Chalkidis, Laura Cabello, Stephanie Brandl
Publié dans: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2023.emnlp-main.427

Llama meets EU: Investigating the European political spectrum through the lens of LLMs

Auteurs: Ilias Chalkidis, Stephanie Brandl
Publié dans: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), 2024
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2024.naacl-short.40

Peer reviewed articles (1)

Domain-Specific Word Embeddings with Structure Prediction

Auteurs: David Lassner, Stephanie Brandl, Anne Baillot, Shinichi Nakajima
Publié dans: Transactions of the Association for Computational Linguistics, Numéro 11, 2023, ISSN 2307-387X
Éditeur: MIT Press
DOI: 10.1162/tacl_a_00538