arXiv Machine Learning
Cross-lingual Functional Vectors for Emotion Detection in Large Language Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computation and Language
4d ago
Language Steering for Multilingual In-Context Learning
arXiv:2602.02326v3 Announce Type: replace Abstract: If multilingual language model representations contain separable language-associated structure, then shifting between languages may require only si...
arXiv AI
Jun 29
Do Speech Emphasis Models Generalize across Languages and Emotions?
arXiv:2606. 27717v1 Announce Type: cross Abstract: Prosodic emphasis varies across languages, emotions, and speaking styles, yet existing emphasis detection models are largely trained and evaluated on monolingual neutral read speech.
arXiv Machine Learning
Oct 7
Two Vectors Replace In-Context Demos: Structured Task Adaptation via Embeddings
arXiv:2610.07572v1 Announce Type: cross Abstract: In-context learning (ICL) adapts frozen large multimodal models (LMMs) to new tasks from a few demonstrations (demos), but re-encodes them at every q...
arXiv AI
Sep 15
Disentangling Topology and Diversity in Multi-Agent LLMs for Multilingual Low-Resource Emotion Detection
arXiv:2609.14570v1 Announce Type: cross Abstract: Multi-agent LLM systems combine multiple inference calls, but prior work often confounds how calls are connected with how they are diversified. We st...
arXiv AI
Oct 2
Capturing In-Context Learning Dynamics with Task Operators
arXiv:2610.01054v1 Announce Type: cross Abstract: In-context learning (ICL) enables language models to perform new tasks from demonstrations without weight updates. However, every ICL inference requi...
arXiv Computation and Language
3d ago
Emotion Is Not External Knowledge: Internal Attention Signals for Affective State Reasoning
The paper investigates how large language models (LLMs) handle affective state reasoning, a type of implicit conversational state that persists across topic shifts. It introduces Self‑targeted Internal Attention Boosting (SIAB), a method that identifies and amplifies sparse affective attention heads using causal localization and the model’s own behavior, without relying on external labels. Experiments on ECC and GoEmotions datasets across multiple LLMs and prompting settings show that SIAB improves macro‑F1 scores by up to +10.3 points on ECC and +5.5 on GoEmotions, and further gains are achieved when combined with external supervision.