Tag
This paper introduces FrenchNews-7, a benchmark for classifying French news editorial desks across multiple publishers, featuring a fine-tuned CamemBERT classifier and evaluations against LLM baselines.
This paper analyzes 28,592 French news headlines about La France insoumise and Rassemblement National using an LLM annotation pipeline, finding asymmetric role framing where LFI is more often framed as aggressors and RN as strategic actors.
The paper presents a simple pipeline that uses LLMs to automatically group features into supernodes in attribution graphs, matching human annotator interpretability and recovering intermediate hop supernodes in a two-hop task.
This paper presents a computational approach using large language models and RoBERTa to identify manner and result verbs in sentence context, achieving up to 89.6% accuracy. It aims to provide a scalable measurement tool for developmental language research.
This paper introduces MultiSoc-4D, a benchmark for diagnosing instruction-induced label collapse in LLMs annotating Bengali social media. It reveals that LLMs systematically prefer fallback labels, leading to under-detection of minority categories like hate speech and sarcasm.
Researchers use three open-source LLMs to annotate 10,600 persuader turns in the PersuasionForGood corpus with 41 persuasion strategies, finding that strategy categories explain little donation variance and guilt induction significantly lowers donation rates.