mlsanityData to 14 Oct 2026

SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models

arXiv 2510.16917 ↗First posted 19 Oct 2025cs.SD cs.AI cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

Knowledge editing enables targeted updates without retraining, but prior work focuses on textual or visual facts, leaving abstract auditory perceptual knowledge underexplored. We introduce SAKE, the first benchmark for editing perceptual auditory attribute knowledge in large audio-language models (LALMs), which requires modifying acoustic generalization rather than isolated facts. We evaluate eight diverse editing methods on three LALMs across reliability, generality, locality, and portability, under single and sequential edits. Results show that most methods enforce edits reliably but struggle with auditory generalization, intra-attribute locality, and multimodal knowledge propagation, and often exhibit forgetting or degeneration in sequential editing. Additionally, fine-tuning the modality connector emerges as a more robust and balanced baseline compared with directly editing the LLM backbones. SAKE reveals key limitations of current methods and provides a foundation for developing auditory-specific LALM editing techniques.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 59 of its 66 references that are in the map. First posted on arXiv 19 Oct 2025.

Builds on

59 of 66 references.

References · 59

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  4. 2023Visual Instruction Tuningcited by 7,869
  5. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  6. 2024GPT-4o System Cardcited by 4,588
  7. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  8. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  9. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  10. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  11. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  12. 2022Mass-Editing Memory in a Transformercited by 1,001
38 more
  1. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 734
  2. 2023Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Modelscited by 608
  3. 2024Qwen2-Audio Technical Reportcited by 560
  4. 2021Editing Factual Knowledge in Language Modelscited by 553
  5. 2023SALMONN: Towards Generic Hearing Abilities for Large Language Modelscited by 506
  6. 2021Fast Model Editing at Scalecited by 498
  7. 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 372
  8. 2024MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmarkcited by 288
  9. 2023Can We Edit Factual Knowledge by In-Context Learning?cited by 285
  10. 2025Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Modelscited by 219
  11. 2024Mini-Omni: Language Models Can Hear, Talk While Thinking in Streamingcited by 210
  12. 2024VoiceBench: Benchmarking LLM-Based Voice Assistantscited by 200
  13. 2024LLaMA-Omni: Seamless Speech Interaction with Large Language Modelscited by 173
  14. 2025Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilitiescited by 133
  15. 2025MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mixcited by 117
  16. 2025MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmarkcited by 103
  17. 2023Joint Audio and Speech Understandingcited by 100
  18. 2023EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Modelscited by 98
  19. 2024Model Editing at Scale leads to Gradual and Catastrophic Forgettingcited by 93
  20. 2024Detoxifying Large Language Models via Knowledge Editingcited by 87
  21. 2025AnyEdit: Edit Any Knowledge Encoded in Language Modelscited by 76
  22. 2024Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Taskscited by 71
  23. 2024The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapsecited by 54
  24. 2025DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignmentcited by 50
  25. 2024DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Datacited by 45
  26. 2023Can We Edit Multimodal Large Language Models?cited by 44
  27. 2025SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Informationcited by 42
  28. 2025Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Surveycited by 39
  29. 2024Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Modelscited by 37
  30. 2024VLKEB: A Large Vision-Language Model Knowledge Editing Benchmarkcited by 30
  31. 2024Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generationcited by 27
  32. 2025Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Modelscited by 27
  33. 2025STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Modelscited by 26
  34. 2024Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedbackcited by 23
  35. 2024Building a Taiwanese Mandarin Spoken Language Model: A First Attemptcited by 23
  36. 2025MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledgecited by 23
  37. 2024MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistencycited by 22
  38. 2024Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Modelscited by 21

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026All That Glitters Is Not Audio: Rethinking Text Priors and Audio Reliance in Audio-Language Evaluationcited by 8
  2. 2026MUGEN: Evaluating and Improving Multi-audio Understanding of Large Audio-Language Modelscited by 2
  3. 2026Nudging Hidden States: Training-Free Model Steering for Chain-of-Thought Reasoning in Large Audio-Language Modelscited by 2
  4. 2026When Demonstrations Fail: Diagnosing the Limits of In-Context Learning in Large Audio-Language Models with Progressive Cue Removalcited by 0
  5. 2026Encoder-Side Neuron Identification and Amplification for Acoustic Perception in Large Audio-Language Modelscited by 0