Incomplete constrainers in constrained decoding push LLMs into low-probability program regions, making unconstrained decoding outperform constrained decoding on functional correctness across seven models and three benchmarks.
arXiv:2506.05754 [cs.AI] https://arxiv.org/abs/2506.05754
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
LenVM trains a token-level value head to predict discounted remaining length, enabling length control and efficiency steering on LLMs and VLMs.
A twisted sequential Monte Carlo decoder with surface automata improves exact constraint satisfaction in structured text generation over standard decoding baselines across three benchmarks.
TreeCoder improves LLM code generation accuracy by representing decoding as an optimizable tree search over programs with first-class constraints for syntax, style, and execution, outperforming baselines on MBPP and SQL-Spider.
SelPE introduces a selection-guided progressive evolution method for private structured text synthesis that decouples abstraction from schema realization and claims better validity and utility under tight DP budgets in low-data settings.
citing papers explorer
-
The Alignment Problem in Constrained Code Generation
Incomplete constrainers in constrained decoding push LLMs into low-probability program regions, making unconstrained decoding outperform constrained decoding on functional correctness across seven models and three benchmarks.
-
Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling
LenVM trains a token-level value head to predict discounted remaining length, enabling length control and efficiency steering on LLMs and VLMs.
-
LatticeBridge: Rare-Event Sequential Inference for Faithful Structured Sequence Synthesis
A twisted sequential Monte Carlo decoder with surface automata improves exact constraint satisfaction in structured text generation over standard decoding baselines across three benchmarks.
-
TreeCoder: Systematic Exploration and Optimisation of Decoding and Constraints for LLM Code Generation
TreeCoder improves LLM code generation accuracy by representing decoding as an optimizable tree search over programs with first-class constraints for syntax, style, and execution, outperforming baselines on MBPP and SQL-Spider.
-
SelPE: Progressive Selection for Private Structured Text Synthesis
SelPE introduces a selection-guided progressive evolution method for private structured text synthesis that decouples abstraction from schema realization and claims better validity and utility under tight DP budgets in low-data settings.