TruncProof lets LLMs generate syntactically valid JSON within strict token limits by approximating completion token counts via LL(1) parser lookahead.
SynCode.arXiv:2403.01632, March
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
AloLab, an iterative meta-agent prompt optimizer, raises structured output accuracy for 7-9B models from 0% to 84-87% on GSM8K while preserving near-native inference speed.
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.
RefineStat improves small language model performance on probabilistic program synthesis by adding semantic constraint enforcement and diagnostic-aware refinement, producing syntactically and statistically reliable code that often matches larger models.
AdaDec improves Pass@1 accuracy of LLM code generation by up to 20.9% over greedy decoding by triggering lookahead reranking only at high-uncertainty steps on HumanEval+, MBPP+, and DevEval.
Compiled AI generates deterministic code artifacts from LLMs in a one-time compilation step, enabling reliable workflow execution with zero runtime tokens after break-even.
Fine-tuning codegen-mono on 500 synthetic-plus-reviewed Python examples produces 99% accuracy, 98.08% precision, 100% recall and 99.04% F1 for CWE detection.
citing papers explorer
-
TruncProof: A Guardrail for LLM-based JSON Generation under Token-Length Constraints
TruncProof lets LLMs generate syntactically valid JSON within strict token limits by approximating completion token counts via LL(1) parser lookahead.
-
When Correct Isn't Usable: Improving Structured Output Reliability in Small Language Models
AloLab, an iterative meta-agent prompt optimizer, raises structured output accuracy for 7-9B models from 0% to 84-87% on GSM8K while preserving near-native inference speed.
-
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.
-
RefineStat: Efficient Exploration for Probabilistic Program Synthesis
RefineStat improves small language model performance on probabilistic program synthesis by adding semantic constraint enforcement and diagnostic-aware refinement, producing syntactically and statistically reliable code that often matches larger models.
-
AdaDec: A Uncertainty-Guided Lookahead Decoding Framework for LLM-Based Code Generation
AdaDec improves Pass@1 accuracy of LLM code generation by up to 20.9% over greedy decoding by triggering lookahead reranking only at high-uncertainty steps on HumanEval+, MBPP+, and DevEval.
-
Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation
Compiled AI generates deterministic code artifacts from LLMs in a one-time compilation step, enabling reliable workflow execution with zero runtime tokens after break-even.
-
Case Study: Fine-tuning Small Language Models for Accurate and Private CWE Detection in Python Code
Fine-tuning codegen-mono on 500 synthetic-plus-reviewed Python examples produces 99% accuracy, 98.08% precision, 100% recall and 99.04% F1 for CWE detection.