A new conservative confidence rejection criterion for proxy-guided test-time alignment of language models unifies prior implicit reward and nudging approaches while outperforming them on datasets by handling linguistic ambiguity better.
In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Lin- guistics (Volume 1: Long Papers), pages 3854–3872, Rabat, Morocco
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the Rejection Criterion for Proxy-based Test-time Alignment
A new conservative confidence rejection criterion for proxy-guided test-time alignment of language models unifies prior implicit reward and nudging approaches while outperforming them on datasets by handling linguistic ambiguity better.