K-FinHallu Benchmark

What is K-FinHallu?

Evaluates hallucination detection in multi-turn Korean financial RAG dialogues, with a taxonomy based on context answerability. Includes training and test…

Released

2026-05-28

Evaluates

Finance, Vision & 3D, cs.LG

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2605.29523

K-FinHallu paper

• Paper https://arxiv.org/abs/2605.29523

Which sources cite K-FinHallu?

• K-FinHallu

Related Finance, Vision & 3D, cs.LG benchmarks

• A Large-Scale Dataset and Benchmark
• ActiveVision
• AD-Diff Bench
• AdvPlan-Bench
• AE-UAV
• AeroGround
• Agentic Infrastructure ChangeBench
• AGI Maze Prediction Datasets and Benchmark