GPT-4o extracts inflation narratives with 44% accuracy against an expert gold standard, well below the 67-74% of human annotators, but in valid structured form.
Sometimes, there is a strong temptation to omit parts of a sentence in order to make the narrative more pointed
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
econ.GN 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Identifying economic narratives in large text corpora -- An integrated approach using Large Language Models
GPT-4o extracts inflation narratives with 44% accuracy against an expert gold standard, well below the 67-74% of human annotators, but in valid structured form.