Causal Localization of the Refusal Direction in Audio Language Models

arXiv:2609.22260 · cs.MM, cs.CL, cs.LG, cs.SD, eess.AS · Submitted 2026-09-06 · Read on arXiv

cs.MM, cs.CL, cs.LG, cs.SD, eess.AS

Submitted: 2026-09-06

Updated: 2026-09-06

Comments: Accepted at ISCSLP 2026. 4 pages + references

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Ablation — 2× in this paper · explained in 1 episode

Related papers

• ControlFoley: Unified and Controllable Video-to-Audio Generation with Cross-Modal Conflict Handling
• Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models
• Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection
• A Rate-Distortion-Classification Approach for Lossy Image Compression