SOURCE-LINKED INTELLIGENCE

Cross-lingual Functional Vectors for Emotion Detection in Large Language Models

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

Function vectors (FVs) have recently emerged as a promising mechanism for steering the behavior of large language models (LLMs) by injecting task-specific latent direction representations derived from in-context demonstrations. While prior studies have shown that FVs can recover task behavior in structured in-context learning settings, their effectiveness on semantically complex tasks and their ability to generalize across languages remain underexplored. We investigate the cross-lingual transferability of FVs using multilingual multi-label emotion recognition as a challenging semantic classifi

Read original source ↗ Open in workspace

recordType

paper

region

Global