Human-written narrative descriptions boost zero-shot hidden-narrative detection; few-shot examples often hurt
Authors self-report: on Dipromats and SemEval, human-written narrative descriptions significantly improve LLMs' zero-shot detection of hidden narratives in social messaging, while auto-generated descriptions or few-shot examples often reduce accuracy.
ImportanceLocalEvidenceE2 unreplicated
Providing large language models with human-written narrative descriptions significantly improves their zero-shot accuracy at detecting hidden narratives in social messaging; combined with majority-vote ensembling, the authors claim performance comparable to supervised systems.
The prior approach relied on auto-generated descriptions or few-shot examples, but these often reduced accuracy due to subtle framing shifts.
The measurement was run on the Dipromats and SemEval datasets, and the results are self-reported by the three authors, not independently verified.
Boundary: no third-party replication yet; the preprint was submitted September 15 and revised as v2 on September 16 (arXiv:2609.17310).