<ul><li>Researchers have tested the annotation of focalization in literature using large language models (LLMs).</li><li>The study found that LLMs performed comparable to trained human annotators, achieving an average F1 score of 84.79%.</li><li>The log probabilities output by GPT-family models reflected the difficulty of annotating specific literary excerpts.</li><li>The research highlights the potential of LLMs for computational literary studies and insights into focalization in literature.</li></ul>

Says Who? Effective Zero-Shot Annotation of Focalization

Discover more