Causal Tracing of Audio-Text Fusion in Large Audio Language Models

arXiv:2603.13768 · cs.SD, cs.CL · Submitted 2026-03-14 · Read on arXiv

cs.SD, cs.CL

Submitted: 2026-03-14

Updated: 2026-09-23

Terminology

• Benchmark — 10× in this paper · explained in 2 episodes
• Interpretability — 10× in this paper · explained in 15 episodes
• Transformer — 10× in this paper · explained in 2 episodes
• Hallucination — 9× in this paper · explained in 3 episodes
• Mechanistic interpretability — 7× in this paper · explained in 2 episodes
• Recovery Rate — 5× in this paper
• Representation Learning — 3× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• IEEE Automatic Speech Recognition and Understanding Workshop — 2× in this paper
• Self-Supervised Learning — 2× in this paper · explained in 8 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Hallucination Mitigation — 1× in this paper · explained in 2 episodes
• IEEE Spoken Language Technology Workshop — 1× in this paper
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-hop Reasoning — 1× in this paper · explained in 3 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Structural Integrity — 1× in this paper · explained in 3 episodes

Sources

• The Llama 3 Herd of Models
• Qwen Technical Report
• Qwen2 Technical Report
• Qwen2.5 Technical Report
• Qwen3 Technical Report
• Ministral 3
• DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment
• Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models
• Qwen2-Audio Technical Report
• Voxtral
• BEATs: Audio Pre-Training with Acoustic Tokenizers

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