A receiver-conditioned token reranker, trained on a fixed answer-verified continuation, improves collaborative math decoding over LLM-local-preference baselines.
Findings of the Association for Computational Linguistics: ACL 2026 , year =
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
-
FutureBridge: Token Selection Beyond Local Preference in Collaborative Decoding
A receiver-conditioned token reranker, trained on a fixed answer-verified continuation, improves collaborative math decoding over LLM-local-preference baselines.