A 1,834-question Indonesian dilemma benchmark shows leading LLMs match Indonesian human choices only about half the time and struggle most on religion and unity.
Kilmann and Kenneth W
1 Pith paper cite this work, alongside 570 external citations. Polarity classification is still indexing.
1
Pith paper citing it
570
external citations · OpenAlex
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pancasila-Dilemmas: Evaluating Large Language Models on Indonesian Human Value Dilemmas Grounded in Pancasila
A 1,834-question Indonesian dilemma benchmark shows leading LLMs match Indonesian human choices only about half the time and struggle most on religion and unity.