AOR-Bench: Do Large Audio Language Models Over-Refuse Pseudo-Harmful Queries?
Large Audio Language Models (LALMs) have demonstrated strong performance across a wide range of audio tasks. As they are increasingly deployed in real-world applications, ensuring their safety alignment has become more important. Although refusal mechanisms serve as a key safeguard by preventing LALMs from responding to harmful requests, they can also lead to {\em over-refusal}, where models incorrectly reject benign queries. This issue is especially challenging in the audio domain because speec
Record details
Published: 19 June 2026
Source: arXiv
Category: Research
Topics: Safety & alignment
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Aligning Sentence Embeddings to Human Concepts via Sparse Autoencoders
arXiv · 19 June 2026
Graph-of-Differences: Anatomy-Structured Difference Alignment for Medical Image Re-Identification
arXiv · 19 June 2026
AI Alignment From Social Choice Perspectives
arXiv · 19 June 2026
Cross-Modal Corroboration for Annotation-Free Wildlife Monitoring
arXiv · 19 June 2026
Imitation from Heterogeneous Demonstrations using Grounded Latent-Action World Models
arXiv · 19 June 2026
What Shapes Emergent Misalignment? Insights from Training Dynamics, Model Priors, and Data
arXiv · 18 June 2026
How to cite this record
ethics.ai (19 June 2026), “AOR-Bench: Do Large Audio Language Models Over-Refuse Pseudo-Harmful Queries?,” evidence record 775, https://ethics.ai/record/775 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.