"Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understanding

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Koudounas, Alkis, Savelli, Claudio, Giobergia, Flavio, Baralis, Elena
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912773848432640
author Koudounas, Alkis
Savelli, Claudio
Giobergia, Flavio
Baralis, Elena
author_facet Koudounas, Alkis
Savelli, Claudio
Giobergia, Flavio
Baralis, Elena
contents Machine unlearning, the process of efficiently removing specific information from machine learning models, is a growing area of interest for responsible AI. However, few studies have explored the effectiveness of unlearning methods on complex tasks, particularly speech-related ones. This paper introduces UnSLU-BENCH, the first benchmark for machine unlearning in spoken language understanding (SLU), focusing on four datasets spanning four languages. We address the unlearning of data from specific speakers as a way to evaluate the quality of potential "right to be forgotten" requests. We assess eight unlearning techniques and propose a novel metric to simultaneously better capture their efficacy, utility, and efficiency. UnSLU-BENCH sets a foundation for unlearning in SLU and reveals significant differences in the effectiveness and computational feasibility of various techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15700
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle "Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understanding
Koudounas, Alkis
Savelli, Claudio
Giobergia, Flavio
Baralis, Elena
Computation and Language
Sound
Audio and Speech Processing
Machine unlearning, the process of efficiently removing specific information from machine learning models, is a growing area of interest for responsible AI. However, few studies have explored the effectiveness of unlearning methods on complex tasks, particularly speech-related ones. This paper introduces UnSLU-BENCH, the first benchmark for machine unlearning in spoken language understanding (SLU), focusing on four datasets spanning four languages. We address the unlearning of data from specific speakers as a way to evaluate the quality of potential "right to be forgotten" requests. We assess eight unlearning techniques and propose a novel metric to simultaneously better capture their efficacy, utility, and efficiency. UnSLU-BENCH sets a foundation for unlearning in SLU and reveals significant differences in the effectiveness and computational feasibility of various techniques.
title "Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understanding
topic Computation and Language
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2505.15700