LLMs show limited parametric knowledge for conflict forecasting; adding retrieved context from GDELT and ACLED improves GPT-4's predictions modestly but does not help LLaMA-2.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Do Large Language Models Know Conflict? Investigating Parametric vs. Non-Parametric Knowledge of LLMs for Conflict Forecasting
LLMs show limited parametric knowledge for conflict forecasting; adding retrieved context from GDELT and ACLED improves GPT-4's predictions modestly but does not help LLaMA-2.