A comparison of GPT-3.5, GPT-4o, and o1-mini on few-shot named entity recognition over a new 153-event mass-shooting dataset finds GPT-4o most accurate, though the dataset and evaluation details are not fully disclosed.
From data to knowledge: Building a single source of truth,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Knowledge Acquisition on Mass-shooting Events via LLMs for AI-Driven Justice
A comparison of GPT-3.5, GPT-4o, and o1-mini on few-shot named entity recognition over a new 153-event mass-shooting dataset finds GPT-4o most accurate, though the dataset and evaluation details are not fully disclosed.