A framework learns context-sensitive constraints automatically from LLM outputs to enforce perfect adherence during generation without manual specification.
Title resolution pending
8 Pith papers cite this work, alongside 12 external citations. Polarity classification is still indexing.
8
Pith papers citing it
12
external citations · OpenAlex
representative citing papers
Constrained decoding derived from OpenAPI specifications eliminates hallucinated web API calls in LLM-generated code and substantially improves correctness across 24 models, while retrieval-augmented generation yields inconsistent, model-dependent gains.
Context-aware distillation with BNF+API+vocabulary scales PolkitBench to 10,073 pairs at 99.7% runtime pass rate; ablation on GigaChat-10B shows vocabulary adds +0.198 combined score while API/BNF add 22-25pp structural validity.
EPIC reduces CFG-constrained inference time in diffusion LMs by up to 67.5% via lexing memoization, Earley-style parsing, and relaxed compatible subset selection for parallel commits.
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.
-
Mitigating Errors in LLM-Generated Web API Invocations via Retrieval-Augmented Generation and Constrained Decoding
Constrained decoding derived from OpenAPI specifications eliminates hallucinated web API calls in LLM-generated code and substantially improves correctness across 24 models, while retrieval-augmented generation yields inconsistent, model-dependent gains.
-
Context-Aware Distillation and Ablation for Text2DSL
Context-aware distillation with BNF+API+vocabulary scales PolkitBench to 10,073 pairs at 99.7% runtime pass rate; ablation on GigaChat-10B shows vocabulary adds +0.198 combined score while API/BNF add 22-25pp structural validity.
-
EPIC: Efficient and Parallel Inference under CFG Constraints for Diffusion Language Models
EPIC reduces CFG-constrained inference time in diffusion LMs by up to 67.5% via lexing memoization, Earley-style parsing, and relaxed compatible subset selection for parallel commits.
-
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.