A framework learns context-sensitive constraints automatically from LLM outputs to enforce perfect adherence during generation without manual specification.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
Decoding Time Verification (DTV) interleaves verifier calls at structural boundaries during autoregressive code generation for C-to-Rust and JavaScript-to-TypeScript translation, raising pass rates while using fewer tokens than post-hoc baselines.
ContentFuzz rewrites posts with LLM guidance from stance model confidence to flip machine labels without altering human intent, tested across four models and three datasets in two languages.
ECPO is a listwise policy optimization method that couples ranking utility with span-level evidence certificate validity and a deterministic verifier reward on MAVEN-ERE and RAMS datasets.
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
-
Learning and Enforcing Context-Sensitive Control for LLMs
A framework learns context-sensitive constraints automatically from LLM outputs to enforce perfect adherence during generation without manual specification.
-
Verifier-Guided Code Translation via Meta-Step Decoding
Decoding Time Verification (DTV) interleaves verifier calls at structural boundaries during autoregressive code generation for C-to-Rust and JavaScript-to-TypeScript translation, raising pass rates while using fewer tokens than post-hoc baselines.
-
Content Fuzzing for Escaping Information Cocoons on Digital Social Media
ContentFuzz rewrites posts with LLM guidance from stance model confidence to flip machine labels without altering human intent, tested across four models and three datasets in two languages.
-
ECPO: Evidence-Coupled Policy Optimization for Evidence-Certified Candidate Ranking
ECPO is a listwise policy optimization method that couples ranking utility with span-level evidence certificate validity and a deterministic verifier reward on MAVEN-ERE and RAMS datasets.
-
$\texttt{SEM-CTRL}$: 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.