Beam Search, Self-Consistency, and the Limits of Inference-Time Scaling for Grammar-Constrained Text-to-SQL in Small Language Models
cs.CL, cs.AI
Submitted: 2026-08-26
Updated: 2026-08-26
Terminology
Sources
- Query and Conquer: Execution-Guided SQL Generation
- XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models
- Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning
- A Call for Clarity in Beam Search: How It Works and When It Stops
- Correcting Length Bias in Neural Machine Translation
- The EOS Decision and Length Extrapolation
- Grammar-Aligned Decoding
- Qwen2.5 Technical Report
- PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Consistency of a Recurrent Language Model With Respect to Incomplete Decoding
- Efficient Guided Generation for Large Language Models
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Breaking the Beam Search Curse: A Study of (Re-)Scoring Methods and Stopping Criteria for Neural Machine Translation
- Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering