Multilingual Emotion Neurons in Large Audio-Language Models

arXiv:2608.08772 · cs.CL, eess.AS · Submitted 2026-08-09 · Read on arXiv

Xiutian Zhao, Philipp Koehn, Björn Schuller, Berrak Sisman

cs.CL, eess.AS

Submitted: 2026-08-09

Updated: 2026-08-11

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

Terminology

• Steering — 33× in this paper · explained in 2 episodes
• Consistency — 15× in this paper · explained in 3 episodes
• Accuracy — 12× in this paper · explained in 1 episode
• Interpretability — 8× in this paper · explained in 15 episodes
• Low-Resource Languages — 7× in this paper · explained in 4 episodes
• Benchmark — 5× in this paper · explained in 2 episodes
• Foundation Model — 5× in this paper · explained in 3 episodes
• Foundation Models — 5× in this paper · explained in 8 episodes
• Generalization — 5× in this paper · explained in 14 episodes
• Papers — 5× in this paper · explained in 3 episodes
• Activation Steering — 4× in this paper · explained in 7 episodes
• Robustness — 4× in this paper · explained in 6 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Cross-lingual Transfer — 3× in this paper · explained in 2 episodes
• Universality — 3× in this paper · explained in 2 episodes
• Augmentation — 2× in this paper · explained in 2 episodes
• Contrastive Learning — 2× in this paper · explained in 9 episodes
• Generalizability — 2× in this paper · explained in 6 episodes
• Vision-language models — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Data Augmentation — 1× in this paper · explained in 10 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Decoder — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Ensemble Learning — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Instruction Tuning — 1× in this paper · explained in 3 episodes
• Jaccard Similarity Coefficient — 1× in this paper
• Regularization — 1× in this paper · explained in 3 episodes
• Sparsity — 1× in this paper · explained in 5 episodes
• Sufficiency — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 5 episodes
• Transformers — 1× in this paper · explained in 2 episodes

Sources

• MERaLiON-AudioLLM: Bridging Audio and Language with Large Language Models
• MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models
• Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
• Kimi-Audio Technical Report
• GLU Variants Improve Transformer
• Multimodal Large Language Models Meet Multimodal Emotion Recognition and Reasoning: A Survey
• Decoding Emotions: A comprehensive Multilingual Study of Speech Models for Speech Emotion Recognition
• Emotion Concepts and their Function in a Large Language Model
• EmoSteer-TTS: Fine-Grained and Training-Free Emotion-Controllable Text-to-Speech via Activation Steering
• Qwen2.5-Omni Technical Report
• AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models
• MiniCPM-V: A GPT-4V Level MLLM on Your Phone
• Do LLMs "Feel"? Emotion Circuits Discovery and Control
• Neuron-Level Emotion Control in Speech-Generative Large Audio-Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering