Papers with Backus-Naur Form

2 papers
Neuro-Symbolic Query Compiler (2025.findings-acl)

Copied to clipboard

Challenge: Retrieval-Augmented Generation (RAG) systems are limited in their ability to process information in open-source environments.
Approach: They propose a neuro-symbolic framework inspired by linguistic grammar rules and compiler design to formalize complex queries using a minimal yet sufficient Backus-Naur Form grammar.
Outcome: The proposed framework is based on a backus-naur form grammar and compiler design that maintains completeness while minimizing redundancy.
HyGenar: An LLM-Driven Hybrid Genetic Algorithm for Few-Shot Grammar Generation (2025.findings-acl)

Copied to clipboard

Challenge: Existing grammar generation models perform sub-optimally, resulting in inconsistent syntactic and semantic accuracy.
Approach: They propose an LLM-driven hybrid genetic algorithm to optimize grammar generation by inferring grammars from a set of examples and generated in Backus-Naur Form.
Outcome: The proposed algorithm improves syntactic and semantic accuracy of generated grammars across LLMs.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations