D2D distills distributional shifts between a suspected model and its base into a cartridge adapter to amplify and detect stealth biases in LLMs across multiple types.
Why Knowledge Distillation Amplifies Gender Bias and How to Mitigate from the Perspective of
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation
D2D distills distributional shifts between a suspected model and its base into a cartridge adapter to amplify and detect stealth biases in LLMs across multiple types.