Experts annotated 817 short first-person narratives for narrator unreliability, and LLMs classified them with modest macro-F1 scores: best on verbal-tic detection, worst on abstract character-trope matching.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Classifying Unreliable Narrators with Large Language Models
Experts annotated 817 short first-person narratives for narrator unreliability, and LLMs classified them with modest macro-F1 scores: best on verbal-tic detection, worst on abstract character-trope matching.