← Back to all news
arXiv Computation and Language By Jes\'us M. Fraile-Hern\'andez, Anselmo Pe\~nas, Patrick Giedemann

Zero-shot narrative detection in social messaging

Read the original on arXiv Computation and Language →

The paper explores how large language models can detect hidden narratives in social messages without training data. By feeding the models human-written narrative descriptions, performance improves markedly, while automatically generated descriptions or few-shot examples can hurt accuracy. Ensemble techniques, especially majority voting, further boost robustness, and larger models show the best results with less sensitivity to prompts.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv Computation and Language
Sep 11

Characterizing Narrative Content in Web-scale LLM Pretraining Data

The paper presents a detailed examination of narrative elements—agency, setting, and events—within the Dolma web-scale pretraining corpus. Using a framework of 11 interpretable dimensions, the authors hand‑annotated 400 passages, expanded this to a 25,000‑passage LLM‑labeled dataset, and trained NarraBERT models to predict narrative features across 13 million passages, producing the NarraDolma dataset. The study reveals that narrative structure is measurable at scale and that narrative qualities vary unevenly across different data sources, topics, and formats, highlighting gaps in current data curation practices.

By Teagan Johnson, Elliott Ash, Andrew Piper, Maria Antoniak
llms
More like this →
arXiv Computation and Language
Oct 23

Interpretive Variation and Discourse Structure in Detecting Enthymemes in Controversial Political Discourse

The paper investigates how to detect enthymemes—arguments with unstated premises or conclusions—in controversial political tweets about vaccination and immigration. Despite extensive fine‑tuning, models achieve an F1 score of only about 0.67, prompting the authors to propose new evaluation metrics that compare predictions to the full distribution of annotator votes and a model that directly predicts this distribution. The study also shows that models rely on explicit argumentative structure, often missing implicit links that readers must infer, raising concerns for content moderation systems that depend on majority labels.

By Martial Pastor, Nelleke Oostdijk
fine-tuning
More like this →