Pancasila-Dilemmas Benchmark

What is Pancasila-Dilemmas?

An evaluation dataset of 1,834 dilemma questions from Indonesian news that measures LLM alignment with the five Pancasila values, scored by PMS and MVAS…

Released

2026-07-20

Evaluates

General AI, Language & Knowledge, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.18066

Pancasila-Dilemmas paper and code

• Paper https://arxiv.org/abs/2607.18066
• Code https://github.com/tjunlp-lab/Pancasila-Dilemmas

Which sources cite Pancasila-Dilemmas?

• Pancasila-Dilemmas

Related General AI, Language & Knowledge, cs.CL benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench