List your company

Natural Language Explanation Generation on HealthVer (test)

0.033FaithfulnessCLUE-Span+Steering
-0.11052-0.07326-0.0360.00126May 23, 2025

Evaluation results

MethodLinks
CLUE-Span+SteeringModel=Qwen2.5-14B2025.050.0330.440.530.8
CLUE-Span+SteeringModel=Gemma-2-9B-IT2025.050.0210.390.50.85
CLUE-Span+SteeringModel=OLMo-2-1124-13B2025.050.020.230.770.68
CLUE-SpanModel=Gemma-2-9B-IT2025.050.0070.340.590.82
CLUE-SpanModel=Qwen2.5-14B2025.050.0060.330.680.75
CLUE-SpanModel=OLMo-2-1124-13B2025.050.0050.10.830.61
PromptBaselineModel=Qwen2.5-14B2025.05-0.028——0.74
PromptBaselineModel=OLMo-2-1124-13B2025.05-0.1——0.55
PromptBaselineModel=Gemma-2-9B-IT2025.05-0.105——0.66