Adaptive trie-guided decoding with document context and tunable penalties improves in-document query auto-completion, outperforming baselines and larger models like LLaMA-3 on seen queries.
Grammar-Constrained Decoding for Structured NLP Tasks without Fine- tuning
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
representative citing papers
AI-native games require runtime generative AI as a non-substitutable core-loop mechanism; a 53-game corpus clusters in language-forward narrative and epistemic designs.
Formalizes Text2DSL, introduces PolkitBench dataset with 4,204 pairs, and shows structured prompt context boosts syntactic validity to 98.6-99.4%, structural validity by up to 35.5 pp, and CodeBLEU by 60-95% on two MoE models.
Corpus-Grounded Feature Diffusion generates synthetic Traditional Chinese IEP training data from 25 seeds to fine-tune a 7B model that reaches BERTScore F1 0.779 on a 10-sample hold-out, beating several larger zero-shot models.
Prefix filters learned by the Palla algorithm capture LLM error patterns and enable constrained sampling that boosts TypeScript compile rates by over 60% for Qwen2.5-1.5B to match larger models.
CourseBlueprint builds a typed pipeline over a 23-lecture biomedical imaging corpus to generate prerequisite-aware, learner-adaptive videos with auditable engagement contracts and slide grounding.
ATLAS-RTC raises first-attempt success on structured LLM generation and tool calling by 20-37.8 points through closed-loop token-level interventions.
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.
CausalSynth combines structural causal models with LLMs and iterative verification to produce synthetic data that respects given causal structures while remaining linguistically natural.
Quantized open-weight LMs on consumer hardware match closed-source API accuracy for LM-enhanced relational operators while delivering 390x lower cost and 3.8x lower latency in the BlendSQL framework.
citing papers explorer
-
DocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion
Adaptive trie-guided decoding with document context and tunable penalties improves in-document query auto-completion, outperforming baselines and larger models like LLaMA-3 on seen queries.
-
AI Native Games: A Survey and Roadmap
AI-native games require runtime generative AI as a non-substitutable core-loop mechanism; a 53-game corpus clusters in language-forward narrative and epistemic designs.
-
Text2DSL: LLM-Based Code Generation for Domain-Specific Languages
Formalizes Text2DSL, introduces PolkitBench dataset with 4,204 pairs, and shows structured prompt context boosts syntactic validity to 98.6-99.4%, structural validity by up to 35.5 pp, and CodeBLEU by 60-95% on two MoE models.
-
Automated IEP Generation from Traditional Chinese Parent-Teacher Interviews via Corpus-Grounded Feature Diffusion
Corpus-Grounded Feature Diffusion generates synthetic Traditional Chinese IEP training data from 25 seeds to fine-tune a 7B model that reaches BERTScore F1 0.779 on a 10-sample hold-out, beating several larger zero-shot models.
-
Learning the Error Patterns of Language Models
Prefix filters learned by the Palla algorithm capture LLM error patterns and enable constrained sampling that boosts TypeScript compile rates by over 60% for Qwen2.5-1.5B to match larger models.
-
CourseBlueprint: A Structured Pipeline for Adaptive Pedagogical Video Generation Grounded in Course Corpora
CourseBlueprint builds a typed pipeline over a 23-lecture biomedical imaging corpus to generate prerequisite-aware, learner-adaptive videos with auditable engagement contracts and slide grounding.
-
ATLAS-RTC: Closing the Loop on LLM Agent Output with Token-Level Runtime Control
ATLAS-RTC raises first-attempt success on structured LLM generation and tool calling by 20-37.8 points through closed-loop token-level interventions.
-
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.
-
CasualSynth: Generating Structurally Sound Synthetic Data
CausalSynth combines structural causal models with LLMs and iterative verification to produce synthetic data that respects given causal structures while remaining linguistically natural.
-
Large Databases Need Small, Open-Weight Language Models
Quantized open-weight LMs on consumer hardware match closed-source API accuracy for LM-enhanced relational operators while delivering 390x lower cost and 3.8x lower latency in the BlendSQL framework.