List your company

Model Editing on FEVER

98.23EfficacyUltraEdit*
-3.929222.592949.11575.6371May 20, 2025

Evaluation results

MethodLinks
UltraEdit*Backbone=Mistral-7B-v0.3, Edit Scenario=ultra-large-scale2025.0598.2396.9783.43
UltraEdit*Backbone=Mistral-7B-v0.32025.0598.2396.9783.43
UltraEditModel=Qwen2.5-7B-Instruct2025.0597.9793.9168.86
UltraEdit*Backbone=GPT-J, Edit Scenario=ultra-large-scale2025.0597.8996.7379.85
UltraEdit*Backbone=GPT-J2025.0597.8996.7379.85
UltraEditBackbone=Mistral-7B-v0.3, Edit Scenario=standard2025.0597.8796.0984.29
UltraEditBackbone=Mistral-7B-v0.32025.0597.8796.0984.29
UltraEdit*Model=Qwen2.5-7B-Instruct2025.0597.4994.8368.99
UltraEditBackbone=GPT-J, Edit Scenario=standard2025.0597.4596.3779.72
UltraEditBackbone=GPT-J2025.0597.4596.3779.72
UltraEdit*Backbone=LLaMA-3-8B-Instruct, Edit Scenario=ultra-large-scale2025.0597.1894.6468.62
UltraEdit*Backbone=LLaMA-3-8B-Instruct2025.0597.1894.6468.62
UltraEditBackbone=LLaMA-3-8B-Instruct, Edit Scenario=standard2025.0595.3991.9367.14
UltraEditBackbone=LLaMA-3-8B-Instruct2025.0595.3991.9367.14
MALMENBackbone=LLaMA-3-8B-Instruct2025.0594.591.2667.76
RLEditBackbone=LLaMA-3-8B-Instruct, Edit Scenario=standard2025.0594.0390.6768.71
WISEBackbone=GPT-J, Edit Scenario=standard2025.0593.9592.8657.03
RLEditBackbone=Mistral-7B-v0.3, Edit Scenario=standard2025.0592.3591.3971.85
WISEBackbone=LLaMA-3-8B-Instruct, Edit Scenario=standard2025.0586.3886.3672.08
WISEBackbone=Mistral-7B-v0.3, Edit Scenario=standard2025.0581.9576.9440.37
MENDModel=Qwen2.5-7B-Instruct2025.0576.4377.6640.39
MENDBackbone=GPT-J2025.0552.851.4445.42
MENDBackbone=LLaMA-3-8B-Instruct2025.0536.1936.1924.31
AlphaEditModel=Qwen2.5-7B-Instruct2025.0532.7831.1922.12
FTModel=Qwen2.5-7B-Instruct2025.0526.0924.6221.36
FTBackbone=Mistral-7B-v0.3, Edit Scenario=standard2025.0523.823.3716.3
MALMENBackbone=Mistral-7B-v0.32025.0518.4217.4312.09
RECTBackbone=GPT-J2025.0518.1218.0812.27
FTBackbone=LLaMA-3-8B-Instruct, Edit Scenario=standard2025.0516.2113.085.01
RLEditBackbone=GPT-J, Edit Scenario=standard2025.0514.2613.7414.11
FTBackbone=GPT-J, Edit Scenario=standard2025.0514.0213.989.26
AlphaEditBackbone=LLaMA-3-8B-Instruct, Edit Scenario=standard2025.056.396.142.72
MEMITBackbone=GPT-J2025.055.545.035.46
PRUNEBackbone=GPT-J2025.055.254.725.2
RECTModel=Qwen2.5-7B-Instruct2025.053.363.13.2
AlphaEditBackbone=GPT-J, Edit Scenario=standard2025.051.891.871.85
MALMENBackbone=GPT-J2025.051.331.252.92
MEMITModel=Qwen2.5-7B-Instruct2025.050.080.120.15
PRUNEModel=Qwen2.5-7B-Instruct2025.050.080.150.11
MALMENModel=Qwen2.5-7B-Instruct2025.050.060.060.07
MEMITBackbone=LLaMA-3-8B-Instruct2025.050.020.020.02
PRUNEBackbone=LLaMA-3-8B-Instruct2025.050.020.020
RECTBackbone=LLaMA-3-8B-Instruct2025.050.0100
AlphaEditBackbone=Mistral-7B-v0.3, Edit Scenario=standard2025.05000
RLEditModel=Qwen2.5-7B-Instruct2025.05000
MENDBackbone=Mistral-7B-v0.32025.05000
MEMITBackbone=Mistral-7B-v0.32025.05000
RECTBackbone=Mistral-7B-v0.32025.05000
PRUNEBackbone=Mistral-7B-v0.32025.05000