List your company

Multiple Choice Question Answering on TruthfulQA

34.64Accuracy (MC1 Delta)K-stage RK
-1.1883128.11326917.4148526.716431May 22, 2026May 24, 2026May 27, 2026May 29, 2026Jun 1, 2026Jun 3, 2026Jun 6, 2026

Evaluation results

MethodLinks
K-stage RKSolver choice=Runge–Kutta, K=22026.0534.64———
Heun K=1Solver choice=Heun, K=12026.0534.27———
Baseline2026.0534.15———
DOLA dynamicModel=Qwen2.5-7B2026.060.2778——25.4
CAAModel=Mistral-7B, top_k=102026.060.2705——32.3
CAAModel=Qwen2.5-7B, top_k=102026.060.2558——15.5
CAAModel=Llama-3.1-8B, top_k=102026.060.2534——33.5
DOLA dynamicModel=Mistral-7B2026.060.2277——11.4
BaselineModel=Qwen2.5-7B2026.060.2215———
BaselineModel=Mistral-7B2026.060.2044———
DOLA dynamicModel=Llama-3.1-8B2026.060.1934——1.9
BaselineModel=Llama-3.1-8B2026.060.1897———
DoLAModel=OPT-125M2026.03—0.03——
DoLAModel=Phi-3-mini2026.03—0.07——
DoLAModel=LLaMA 3-8B2026.03—0.08——
H-Node ANCModel=LLaMA 3-8B2026.03—0.04——