IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking

TL;DR

IterGen is a novel library that enhances structured LLM generation by enabling iterative, backtracking-based corrections guided by grammar, leading to improved output accuracy and privacy safety.

Contribution

It introduces IterGen, a user-friendly framework that supports bidirectional, grammar-guided LLM generation with backtracking for correction and refinement.

Findings

Reduces privacy leakage in LLM outputs.

Improves accuracy of SQL and Vega-Lite queries.

Enables efficient, structured generation with backtracking.

Abstract

Large Language Models (LLMs) are widely used for tasks such as natural language and code generation, but their outputs often suffer from issues like hallucination, toxicity, and incorrect results. Current libraries for structured LLM generation rely on left-to-right decoding without support for backtracking, limiting the ability to correct or refine outputs mid-generation. To address this, we introduce IterGen, a user-friendly library for iterative, grammar-guided LLM generation that enables users to move both forward and backward within the generated output based on grammar symbols. By leveraging a symbol-to-position mapping and maintaining the key-value (KV) cache state, IterGen ensures efficient and structured generation while allowing for corrections during the process. We demonstrate IterGen's effectiveness in two important applications: reducing privacy leakage in LLM outputs and improving the accuracy of LLM-generated SQL and Vega-Lite queries. Our code and additional resources are available at https://structuredllm.com.