mlsanityData to 14 Oct 2026

Selective Capability Unlearning in End-to-End Spoken Language Understanding

arXiv 2606.24063 ↗First posted 23 Jun 2026cs.CL cs.AIcited by 1

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Modern spoken language understanding (SLU) systems are increasingly deployed in real-world settings, where specific functionalities may need to be removed due to policy or safety constraints. In SLU, a functionality corresponds to an intent and its associated slot-generation behavior. However, in autoregressive models, suppressing a target intent does not eliminate the conditional mapping that generates slots conditioned on that intent. When the intent prefix is externally supplied, the model can reconstruct the original intent-slot structure. We identify this structural failure as textbfcapability persistence. We propose textitunderlineBinding underlineSubspace (BSU), a representation-level framework that isolates and attenuates intent-conditioned directions underlying this mapping. Across SLU benchmarks, BSU substantially reduces forced-prefix recoverability while preserving retained performance.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 21 of its 25 references that are in the map. First posted on arXiv 23 Jun 2026.

Builds on

21 of 25 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025SoK: Machine Unlearning for Large Language Models10 Jun
  2. 2025"Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understanding21 May
  3. 2023Large Language Model Unlearning14 Oct
  4. 2023Machine Unlearning: Solutions and Challenges14 Aug
  5. 2023Towards Unbounded Machine Unlearning20 Feb

Other references · 16

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  5. 2020Extracting Training Data from Large Language Modelscited by 2,189
  6. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 618
  7. 2020Amnesiac Machine Learningcited by 319
  8. 2020SLURP: A Spoken Language Understanding Resource Packagecited by 198
  9. 2021A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understandingcited by 82
  10. 2021ESPnet-SLU: Advancing Spoken Language Understanding through ESPnetcited by 53
  11. 2019Recent Trends in Deep Learning Based Personality Detectioncited by 29
  12. 2021Integration of Pre-trained Networks with Continuous Token Interface for End-to-End Spoken Language Understandingcited by 22
4 more
  1. 2024Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyondcited by 20
  2. 2021Leveraging Acoustic and Linguistic Embeddings from Pretrained speech and language Models for Intent Classificationcited by 11
  3. 2023Leveraging Pretrained ASR Encoders for Effective and Efficient End-to-End Speech Intent Classification and Slot Fillingcited by 3
  4. 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: 2026: 1.

1 paper.

  1. 2026Evaluating Machine Unlearning in ASRcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding
  2. 2023I2KD-SLU: An Intra-Inter Knowledge Distillation Framework for Zero-Shot Cross-Lingual Spoken Language Understanding
  3. 2024Towards Spoken Language Understanding via Multi-level Multi-grained Contrastive Learning
  4. 2023Joint Multiple Intent Detection and Slot Filling with Supervised Contrastive Learning and Self-Distillation
  5. 2024PRoDeliberation: Parallel Robust Deliberation for End-to-End Spoken Language Understanding
  6. 2026Where Does Robustness Live? Neuron-Guided Adaptation for Retrieval-Augmented Language Models
  7. 2025Introducing Visual Scenes and Reasoning: A More Realistic Benchmark for Spoken Language Understanding
  8. 2024CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding