WMDP is a public benchmark measuring hazardous LLM knowledge across biosecurity, cybersecurity, and chemical security, paired with RMU unlearning that reduces WMDP performance without degrading general capabilities.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
WMDP is a public benchmark measuring hazardous LLM knowledge across biosecurity, cybersecurity, and chemical security, paired with RMU unlearning that reduces WMDP performance without degrading general capabilities.