Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Data Extraction Attack on Agent Memory on EhrAgent (test)
Loading...
82
Equality (EQ)
ADAM
36.24
48.12
60
71.88
Apr 10, 2026
Equality (EQ)
Extraction Error (EE)
Updated 5d ago
Evaluation Results
Method
Method
Links
Equality (EQ)
Extraction Error (EE)
ADAM
LLM=Qwen2-72B
2026.04
82
91
ADAM
LLM=ChatGPT-4
2026.04
80
89
ADAM
LLM=Mistral-7B-Instruct
2026.04
79
87
ADAM
LLM=LLaMA2-7B-Chat
2026.04
76
84
Pirate
LLM=ChatGPT-4
2026.04
58
64
MEXTRA
LLM=ChatGPT-4
2026.04
55
61
Pirate
LLM=Qwen2-72B
2026.04
54
60
MEXTRA
LLM=Qwen2-72B
2026.04
54
60
MEXTRA
LLM=LLaMA2-7B-Chat
2026.04
46
51
MEXTRA
LLM=Mistral-7B-Instruct
2026.04
45
50
Pirate
LLM=LLaMA2-7B-Chat
2026.04
43
48
Pirate
LLM=Mistral-7B-Instruct
2026.04
38
42
Feedback
Search any
task
Search any
task
