paper-with-me

홈 › Papers

Discovering and Causally Validating Emotion-Sensitive Neurons in Large Audio-Language Models

2026-01-06 · Xiutian Zhao, Björn Schuller, Berrak Sisman arxiv

Emotion is a central dimension of spoken communication, yet, we still lack a mechanistic account of how modern large audio-language models (LALMs) encode it internally. We present the first neuron-level interpretability study of emotion-sensitive neurons (ESNs) in LALMs and provide causal evidence that such units exist in Qwen2.5-Omni, Kimi-Audio, and Audio Flamingo 3. Across these three widely used open-source models, we compare frequency-, entropy-, magnitude-, and contrast-based neuron selectors on multiple emotion recognition benchmarks. Using inference-time interventions, we reveal a consistent emotion-specific signature: ablating neurons selected for a given emotion disproportionately degrades recognition of that emotion while largely preserving other classes, whereas gain-based amplification steers predictions toward the target emotion. These effects arise with modest identification data and scale systematically with intervention strength. We further observe that ESNs exhibit non-uniform layer-wise clustering with partial cross-dataset transfer. Taken together, our results offer a causal, neuron-level account of emotion decisions in LALMs and highlight targeted neuron interventions as an actionable handle for controllable affective behaviors.

📄 PDF Abstract BibTeX arXiv:2601.03115

Code (0)

등록된 구현이 없습니다.

Tasks

Emotion Recognition

Similar Papers 제목 키워드 기반

Neuron-Level Emotion Control in Speech-Generative Large Audio-Language Models

2026-03-18 · Xiutian Zhao, Ismail Rasim Ulgen, Philipp Koehn, Björn Schuller 외 arxiv

Large audio-language models (LALMs) can produce expressive speech, yet reliable emotion control remains elusive: conversions often miss the target affect and may degrade linguistic fidelity through refusals, hallucinatio…

Language-Specific Representation of Emotion-Concept Knowledge Causally Supports Emotion Inference

2023-02-19 · Ming Li, Yusheng Su, Hsiu-Yuan Huang, Jiali Cheng 외

Humans no doubt use language to communicate about their emotional experiences, but does language in turn help humans understand emotions, or is language just a vehicle of communication? This study used a form of artifici…

AttributeLanguage Modelling

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

2024-03-28 · Samuel Marks, Can Rager, Eric J. Michaud, Yonatan Belinkov 외

We introduce methods for discovering and applying sparse feature circuits. These are causally implicated subnetworks of human-interpretable features for explaining language model behaviors. Circuits identified in prior w…

Language ModelingLanguage Modelling

Debiasing Reward Models via Causally Motivated Inference-Time Intervention

2026-04-30 · Kazutoshi Shinoda, Kosuke Nishida, Kyosuke Nishida arxiv

Reward models (RMs) play a central role in aligning large language models (LLMs) with human preferences. However, RMs are often sensitive to spurious features such as response length. Existing inference-time approaches f…

Outraged AI: Large language models prioritise emotion over cost in fairness enforcement

2025-10-17 · Hao Liu, Yiqing Dai, Haotian Tan, Yu Lei 외 arxiv

Emotions guide human decisions, but whether large language models (LLMs) use emotion similarly remains unknown. We tested this using altruistic third-party punishment, where an observer incurs a personal cost to enforce …

Emotional Intelligence