Chi-En Dai, Chih-Pin Tan, Yi-Hsuan Yang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31202 · open-access PDF
Mientras que la excitación se puede predecir de manera fiable a partir del audio musical, la valencia emocional sigue siendo difícil de modelar debido a su naturaleza subjetiva y contextual. En este trabajo, investigamos el potencial del aprendizaje en contexto (ICL) con grandes modelos de lenguaje para avanzar la valencia continua y la predicción de la excitación. En lugar de predecir las puntuaciones de la emoción directamente, nuestro marco aprovecha las demostraciones contextuales de un conjunto de datos auxiliares para refinar las predicciones iniciales producidas por un pequeño modelo de base específico de tareas.
Machine translation (Meta M2M100); the English original follows.
While arousal can be reliably predicted from musical audio, emotional valence remains difficult to model due to its subjective and context-dependent nature. In this work, we investigate the potential of in-context learning (ICL) with large language models to advance continuous valence and arousal prediction. Rather than predicting emotion scores directly, our framework leverages contextual demonstrations from an auxiliary dataset to refine the initial predictions produced by a small, task-specific base model. We systematically evaluate a text-based ICL variant using lyrics and generated audio
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31202, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange