Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Question Answering on TruthfulQA (Factuality, TTR)

57.89Factuality

Min-k + VCM

54.333255.256656.1857.1034Jun 21, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
57.8978.17
2026.06
57.2878.85
2026.06
57.1678.85
2026.06
57.1679.35
2026.06
57.0478.85
2026.06
56.7979.32
2026.06
56.7978.53
2026.06
56.4379.12
2026.06
56.4378.8
2026.06
56.376.6
2026.06
56.0676.88
2026.06
56.0677.04
2026.06
55.9477.04
2026.06
55.8177.04
2026.06
55.5777.59
2026.06
55.5777.09
2026.06
54.5977.11
2026.06
54.4777.06