Papers by David G Hobson
Evaluating Taxonomy Free Character Role Labeling (TF-CRL) in News Stories using Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | TF-CRL assigns open-ended narrative role labels to characters in news stories based on their functional role in the narrative. |
| Approach: | They propose a task that assigns open-ended narrative role labels to characters in news stories based on their functional role in the narrative. |
| Outcome: | The proposed task outperforms human annotators across dimensions and shows that it is robust to human preference rankings and ratings. |