Derek Ruths — accepted AI-conference papers

2025

Evaluating Taxonomy Free Character Role Labeling (TF-CRL) in News Stories using Large Language Models

David G Hobson, Derek Ruths, Andrew Piper

EMNLP 2025

We introduce Taxonomy-Free Character Role Labeling (TF-CRL); a novel task that assigns open-ended narrative role labels to characters in news stories based on their functional role in the narrative. Unlike fixed taxonomies, TF-CRL enables more nuanced and comparative analysis by generating compositi

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Story Morals: Surfacing value-driven narrative schemas using large language models

David G Hobson, Haiqi Zhou, Derek Ruths, Andrew Piper

EMNLP 2024main

Stories are not only designed to entertain but encode lessons reflecting their authors’ beliefs about the world. In this paper, we propose a new task of narrative schema labelling based on the concept of “story morals” to identify the values and lessons conveyed in stories. Using large language mode…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗