Fork-think with confidence identifies forking points via model confidence in a single path before sampling continuations, cutting tokens up to 30% and runtime up to 57% on reasoning benchmarks while matching or exceeding parallel thinking performance.
and Choi, Yejin , editor =
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
Reproduction confirms PAG boosts generative retrieval effectiveness, but its look-ahead planning signal collapses under intent-preserving typos and query mismatches, reverting performance to unguided decoding.
Re-evaluating controlled text generation systems under standardized conditions reveals that many published performance claims do not hold, highlighting the need for consistent evaluation practices.
SEM-CTRL integrates token-level MCTS with Answer Set Grammars to enforce rich context-sensitive syntactic and semantic constraints on off-the-shelf LLM decoders, enabling guaranteed valid completions.
citing papers explorer
-
Fork-Think with Confidence
Fork-think with confidence identifies forking points via model confidence in a single path before sampling continuations, cutting tokens up to 30% and runtime up to 57% on reasoning benchmarks while matching or exceeding parallel thinking performance.
-
Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval
Reproduction confirms PAG boosts generative retrieval effectiveness, but its look-ahead planning signal collapses under intent-preserving typos and query mismatches, reverting performance to unguided decoding.
-
A Comparative Study of Controlled Text Generation Systems Using Level-Playing-Field Evaluation Principles
Re-evaluating controlled text generation systems under standardized conditions reveals that many published performance claims do not hold, highlighting the need for consistent evaluation practices.
-
$\texttt{SEM-CTRL}$: Semantically Controlled Decoding
SEM-CTRL integrates token-level MCTS with Answer Set Grammars to enforce rich context-sensitive syntactic and semantic constraints on off-the-shelf LLM decoders, enabling guaranteed valid completions.