Articles producció científica> Enginyeria Informàtica i Matemàtiques

Unlearning in Large Language Models: We Are Not There Yet

  • Dades identificatives

    Identificador:  imarina:9432952
    Autors:  Blanco-Justicia, Alberto; Domingo-Ferrer, Josep; Jebreel, Najeeb Moharram; Manzanares-Salor, Benet; Sanchez, David
    Resum:
    The massive adoption of large language models has prompted concerns about how to align them with human ethics and the rule of law. Digital forgetting of undesirable knowledge via machine unlearning is a promising strategy we survey here.
  • Altres:

    Autor segons l'article: Blanco-Justicia, Alberto; Domingo-Ferrer, Josep; Jebreel, Najeeb Moharram; Manzanares-Salor, Benet; Sanchez, David
    Departament: Enginyeria Informàtica i Matemàtiques
    Autor/s de la URV: Blanco Justicia, Alberto / Domingo Ferrer, Josep / Jebreel, Najeeb Moharram Salim / Manzanares Salor, Benet / Sánchez Ruenes, David
    Paraules clau: Reduced inequalities
    Resum: The massive adoption of large language models has prompted concerns about how to align them with human ethics and the rule of law. Digital forgetting of undesirable knowledge via machine unlearning is a promising strategy we survey here.
    Àrees temàtiques: Ciência da computação; Computer science (all); Computer science (miscellaneous); Computer science, hardware & architecture; Computer science, software engineering; Computer science, software, graphics, programming; Engenharias iv; General computer science; Software
    Accès a la llicència d'ús: https://creativecommons.org/licenses/by/3.0/es/
    Adreça de correu electrònic de l'autor: josep.domingo@urv.cat; david.sanchez@urv.cat; najeeb.jebreel@urv.cat; alberto.blanco@urv.cat; benet.manzanares@urv.cat; najeeb.jebreel@urv.cat
    Data d'alta del registre: 2025-02-08
    Versió de l'article dipositat: info:eu-repo/semantics/acceptedVersion
    Enllaç font original: https://ieeexplore.ieee.org/document/10834279
    Referència a l'article segons font original: Computer. 58 (1): 97-100
    Referència de l'ítem segons les normes APA: Blanco-Justicia, Alberto; Domingo-Ferrer, Josep; Jebreel, Najeeb Moharram; Manzanares-Salor, Benet; Sanchez, David (2025). Unlearning in Large Language Models: We Are Not There Yet. Computer, 58(1), 97-100. DOI: 10.1109/mc.2024.3468588
    URL Document de llicència: https://repositori.urv.cat/ca/proteccio-de-dades/
    DOI de l'article: 10.1109/mc.2024.3468588
    Entitat: Universitat Rovira i Virgili
    Any de publicació de la revista: 2025
    Tipus de publicació: Journal Publications
  • Paraules clau:

    Computer Science (Miscellaneous),Computer Science, Hardware & Architecture,Computer Science, Software Engineering,Computer Science, Software, Graphics, Programming,Software
    Reduced inequalities
    Ciência da computação
    Computer science (all)
    Computer science (miscellaneous)
    Computer science, hardware & architecture
    Computer science, software engineering
    Computer science, software, graphics, programming
    Engenharias iv
    General computer science
    Software
  • Documents:

  • Cerca a google

    Search to google scholar