In-context learning binds model outputs to the demonstrated label tokens as an exhaustive vocabulary, overriding semantic plausibility and causing fixation even with homogeneous or nonsense labels.
Zhang, Bernd Bohnet, Luis Rosias, Stephanie Chan, and 1 others
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
In-Context Fixation: When Demonstrated Labels Override Semantics in Few-Shot Classification
In-context learning binds model outputs to the demonstrated label tokens as an exhaustive vocabulary, overriding semantic plausibility and causing fixation even with homogeneous or nonsense labels.