A Hybrid Framework for Song Lyric Annotation Based on Human-LLM Alignment

Rashini Liyanarachchi; Frank Tran; Md Mahmudul Hasan; Aditya Joshi; Erik Meijering

A Hybrid Framework for Song Lyric Annotation Based on Human-LLM Alignment

Computation and Language 2026-06-28 v1 Artificial Intelligence

Authors: Rashini Liyanarachchi , Frank Tran , Md Mahmudul Hasan , Aditya Joshi , Erik Meijering

Abstract

Emotion recognition of song lyrics is a challenging task since lyrics may not necessarily align with the overall emotion of a song. As a result, lyrics annotation remains largely underexplored. Drawing inspiration from research in large language model (LLM) assisted annotation, we examine the alignment between humans and LLMs for annotation of lyrics by creating a new sentence-level dataset of lyrics. Our observations highlight the subjectivity of the task and the inherent challenges. Following this, we present a hybrid annotation framework that optimizes human and LLM annotation by predicting potential misalignment in annotation.

Keywords

lyrics annotation emotion recognition human-LLM alignment hybrid framework dataset

Cite

@article{arxiv.2606.29273,
  title  = {A Hybrid Framework for Song Lyric Annotation Based on Human-LLM Alignment},
  author = {Rashini Liyanarachchi and Frank Tran and Md Mahmudul Hasan and Aditya Joshi and Erik Meijering},
  journal= {arXiv preprint arXiv:2606.29273},
  year   = {2026}
}