mlsanityData to 14 Oct 2026

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

arXiv 2505.15700 ↗First posted 21 May 2025cs.CL cs.SD eess.AScited by 5

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 27 of its 37 references that are in the map. First posted on arXiv 21 May 2025.

Builds on

27 of 37 references.

Closest ancestors · 14

Same direction, newest first

  1. 2024Machine Unlearning in Generative AI: A Survey30 Jul
  2. 2024RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models16 Jun
  3. 2024Gone but Not Forgotten: Improved Benchmarks for Machine Unlearning29 May
  4. 2024Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy2 Mar
  5. 2024TOFU: A Task of Fictitious Unlearning for LLMs11 Jan
  6. 2023Towards Machine Unlearning Benchmarks: Forgetting the Personal Identities in Facial Recognition Systems3 Nov
  7. 2023Fast Model Debias with Machine Unlearning19 Oct
  8. 2023Who's Harry Potter? Approximate Unlearning in LLMs3 Oct
  9. 2023Machine Unlearning: Solutions and Challenges14 Aug
  10. 2023Towards Unbounded Machine Unlearning20 Feb
  11. 2022Knowledge Unlearning for Mitigating Privacy Risks in Language Models4 Oct
  12. 2022Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher17 May
2 more
  1. 2022Towards Adversarial Evaluations for Inexact Machine Unlearning17 Jan
  2. 2021Fast Yet Effective Machine Unlearning17 Nov

Other references · 13

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  2. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  3. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 618
  4. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 601
  5. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 501
  6. 2020SLURP: A Spoken Language Understanding Resource Packagecited by 198
  7. 2019Speech Model Pre-training for End-to-End Spoken Language Understandingcited by 193
  8. 2024Machine Unlearning for Image-to-Image Generative Modelscited by 47
  9. 2019Recent Trends in Deep Learning Based Personality Detectioncited by 29
  10. 2024Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyondcited by 20
  11. 2019The GDPR & Speech Data: Reflections of Legal and Technology Communities, First Steps towards a Common Understandingcited by 19
  12. 2024A Contrastive Learning Approach to Mitigate Bias in Speech Modelscited by 9
1 more
  1. 2024From Speech to Data: Unraveling Google's Use of Voice Data for User Profilingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2026Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarkscited by 7
  2. 2025Protecting Bystander Privacy via Selective Hearing in Audio LLMscited by 2
  3. 2025FAME: Fictional Actors for Multilingual Erasurecited by 1
  4. 2026Selective Capability Unlearning in End-to-End Spoken Language Understandingcited by 1
  5. 2026Evaluating Machine Unlearning in ASRcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Machine Unlearning of Pre-trained Large Language Models
  2. 2025BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain Overlap
  3. 2025Speech Unlearning
  4. 2024MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearning
  5. 2026Unlearning in LLMs: Methods, Evaluation, and Open Challenges
  6. 2026μ2-Bench: A Multilingual Machine Unlearning Benchmark
  7. 2026Are We Really Measuring Forgetting? Pitfalls in Evaluating Machine Unlearning for Multimodal LLMs
  8. 2025Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs