Can We Read the Mind of an Audio LLM? A Verbalizable, Multilingual Middle-Layer Workspace
cs.SD, cs.AI, cs.CL
Submitted: 2026-08-25
Updated: 2026-08-25
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
- Eliciting Latent Predictions from Transformers with the Tuned Lens
- Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards
- Verbalizable Representations Form a Global Workspace in Language Models
- Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
- Measuring Faithfulness in Chain-of-Thought Reasoning
- ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models
- Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation
- Qwen3-Omni Technical Report
- Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
- Qwen2.5-Omni Technical Report
Related papers
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
- SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
- WASIL: In-the-Wild Arabic Spoken Interactions with LLMs
- Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment