# Extending Confidence-Based Text2Cypher with Grammar and Schema Aware Filtering

arXiv: https://arxiv.org/abs/2605.10318 · HTML: https://mlsanity.com/paper/2605.10318/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 11 May 2026.

## Builds on (most cited first, 22 of 22)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019)
- [Deep Think with Confidence](https://mlsanity.com/paper/2508.15260/) (2025)
- [Scalable Best-of-N Selection for Large Language Models via Self-Certainty](https://mlsanity.com/paper/2502.18581/) (2025)
- [Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation](https://mlsanity.com/paper/2403.06988/) (2024)
- [TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generation](https://mlsanity.com/paper/1804.09769/) (2018)
- [Grammar-Aligned Decoding](https://mlsanity.com/paper/2405.21047/) (2024)
- [A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions](https://mlsanity.com/paper/2208.13629/) (2022)
- [RSL-SQL: Robust Schema Linking in Text-to-SQL Generation](https://mlsanity.com/paper/2411.00073/) (2024)
- [E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQL](https://mlsanity.com/paper/2409.16751/) (2024)
- [Text2Cypher: Bridging Natural Language and Graph Databases](https://mlsanity.com/paper/2412.10064/) (2024)
- [Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQL](https://mlsanity.com/paper/2501.12372/) (2025)
- [SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising](https://mlsanity.com/paper/2105.07911/) (2021)
- [Improving Text-to-SQL with Schema Dependency Learning](https://mlsanity.com/paper/2103.04399/) (2021)
- [Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR](https://mlsanity.com/paper/2603.24840/) (2026)
- [Batched Self-Consistency Improves LLM Relevance Assessment and Ranking](https://mlsanity.com/paper/2505.12570/) (2025)
- [Enhancing Text2Cypher with Schema Filtering](https://mlsanity.com/paper/2505.05118/) (2025)
- [Conversational Lexicography: Querying Lexicographic Data on Knowledge Graphs with SPARQL through Natural Language](https://mlsanity.com/paper/2505.19971/) (2025)
- [Grounding Large Language Models in Reaction Knowledge Graphs for Synthesis Retrieval](https://mlsanity.com/paper/2601.16038/) (2026)

## Built on by (most cited first, 1 of 1)

- [CYGNET: Cypher Gate for Neural Execution Triage and Cost Containment](https://mlsanity.com/paper/2606.04645/) (2026)

## Abstract (arXiv)

Large language models (LLMs) allow users to query databases using natural language by translating questions into executable queries. Despite strong progress on tasks such as Text2SQL, Text2SPARQL, and Text2Cypher, most existing methods focus on better prompting, fine-tuning, or iterative refinement. However, they often do not explicitly enforce structural constraints, such as syntactic validity and schema consistency. This can reduce reliability, since generated queries must satisfy both syntax rules and database schema constraints to be executable. In this work, we study how structured constraints can be used in test-time inference for Text2Cypher. We focus on post-generation validation to improve query correctness. We extend a confidence-based inference framework with a sequential filtering process that combines confidence scoring, grammar validation, and schema constraints before final aggregation. This lets us analyze how different constraint types affect generated queries. Our experiments with two instruction-tuned models show that grammar-based filtering improves syntactic validity. Schema-aware filtering further improves execution quality by enforcing consistency with the database structure. However, stronger filtering also increases the number of empty predictions and reduces execution coverage. Overall, we show that adding simple structural checks at test time improves the reliability of Text2Cypher generation, and we provide a clearer view of how syntax and schema constraints contribute differently.