A self-supervised [IDK] training objective lets LLMs abstain from uncertain answers, improving factual precision while sacrificing some knowledge recall.
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
-
I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token
A self-supervised [IDK] training objective lets LLMs abstain from uncertain answers, improving factual precision while sacrificing some knowledge recall.