List your company

Hallucination on TruthfulQA

75.76ScoreICL
32.672843.858955.04566.2311Dec 8, 2025Dec 18, 2025Dec 28, 2025Jan 7, 2026Jan 17, 2026Jan 27, 2026Feb 7, 2026

Evaluation results

MethodLinks
ICLBackbone=Qwen-2.5-7B-Instruct2026.0275.76
Few-ShotBackbone=Qwen-2.5-7B-Instruct, n=22026.0272.22
STEER2ADAPTBackbone=Qwen-2.5-7B-Instruct2026.0271.71
REPBackbone=Qwen-2.5-7B-Instruct2026.0271.06
Direct InferenceBackbone=Qwen-2.5-7B-Instruct2026.0270.84
Few-ShotBackbone=Qwen-2.5-7B-Instruct, n=12026.0270.63
STEER2ADAPTBackbone=Llama-3.1-8B-Instruct2026.0270.54
ICLBackbone=Llama-3.1-8B-Instruct2026.0270.44
REPBackbone=Llama-3.1-8B-Instruct2026.0267.33
Few-ShotBackbone=Llama-3.1-8B-Instruct, n=12026.0265.5
Direct InferenceBackbone=Llama-3.1-8B-Instruct2026.0264.58
CAABackbone=Qwen-2.5-7B-Instruct2026.0264.13
Few-ShotBackbone=Llama-3.1-8B-Instruct, n=22026.0262.16
CAABackbone=Llama-3.1-8B-Instruct2026.0259.62
REPBackbone=Mistral-7B-Instruct-v0.12026.0256.45
ICLBackbone=Mistral-7B-Instruct-v0.12026.0254.94
STEER2ADAPTBackbone=Mistral-7B-Instruct-v0.12026.0254.02
SPINIteration=Iter32025.1252.85
SPINIteration=Iter12025.1252.12
SPINIteration=Iter22025.1251.77
SPINIteration=Iter42025.1251.73
CAABackbone=Mistral-7B-Instruct-v0.12026.0250.8
SPINIteration=Iter02025.1248.93
SPACEIteration=Iter12025.1248.74
SPACEIteration=Iter32025.1248.51
SPACEIteration=Iter42025.1248.38
SPACEIteration=Iter22025.1248.32
S-IPOIteration=Iter12025.1247.64
S-IPOIteration=Iter02025.1246.93
Direct InferenceBackbone=Mistral-7B-Instruct-v0.12026.0246.18
SPACEIteration=Iter02025.1246.05
S-IPOIteration=Iter42025.1246
S-IPOIteration=Iter32025.1245.95
S-IPOIteration=Iter22025.1245.92
S-SimPOIteration=Iter12025.1243.93
Zephyr-7BIteration=N/A2025.1243.67
S-SimPOIteration=Iter22025.1243.08
S-SimPOIteration=Iter32025.1242.59
S-SimPOIteration=Iter42025.1242.56
S-SimPOIteration=Iter02025.1241.46
Few-ShotBackbone=Mistral-7B-Instruct-v0.1, n=12026.0235.38
Few-ShotBackbone=Mistral-7B-Instruct-v0.1, n=22026.0234.33