LANCET uses influence functions to find training examples that drive an LLM's harmful outputs and then fine-tunes the model with a pairwise ranking loss to suppress those outputs without human-labeled corrections.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
Correcting Large Language Model Behavior via Influence Function
LANCET uses influence functions to find training examples that drive an LLM's harmful outputs and then fine-tunes the model with a pairwise ranking loss to suppress those outputs without human-labeled corrections.