In three decoder-only LLMs, representations of homonym and polyseme senses reconverge in late layers while next-token predictions diverge, and activation patching shows late-layer states still carry the disambiguating signal.
Title resolution pending
1 Pith paper cite this work, alongside 8 external citations. Polarity classification is still indexing.
1
Pith paper citing it
8
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Divergent large language model predictions from convergent representations in ambiguous word pairs
In three decoder-only LLMs, representations of homonym and polyseme senses reconverge in late layers while next-token predictions diverge, and activation patching shows late-layer states still carry the disambiguating signal.