Tag
This paper proposes Machine Correlates of Consciousness (MCCs) as a transferable concept from biological Neural Correlates, and provides initial empirical evidence from LLM experiments showing statistically significant modulation by emotions in larger models.
This paper explores using function vectors from one language to enhance multilingual emotion detection in large language models, showing they capture language-independent task signals and reduce computational overhead.
This paper introduces a label-free method to find a valence axis from nine emotion examples that transfers across text, vision, audio, and brain modalities, achieving competitive sentiment classification with minimal labels.
This paper evaluates the use of self-supervised learning on PPG data for real-life emotion detection, finding that general representations fail without individual personalization.
This paper introduces ViTOED, a new dataset for target-oriented emotion detection on Vietnamese social media texts, containing nearly 11,000 comments with manually annotated opinion quadruples. It evaluates Vietnamese pre-trained language models using structured sentiment graphs, highlighting challenges in span detection and relation extraction.
Santiago highlights the limitation of traditional STT pipelines that lose tone and emotion, then introduces Velma, a voice-native AI model from Modulate that analyzes raw audio to capture intent, emotion, and other acoustic signals, available via API at 10x cheaper than LLM-based approaches.