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.
InProceed- ings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 11468–11478, Suzhou, China
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.