# RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules

arXiv: https://arxiv.org/abs/2607.01293 · HTML: https://mlsanity.com/paper/2607.01293/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 1 Jul 2026.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [Snorkel: Rapid Training Data Creation with Weak Supervision](https://mlsanity.com/paper/1711.10160/) (2017)
- [Symbolic Knowledge Distillation: from General Language Models to Commonsense Models](https://mlsanity.com/paper/2110.07178/) (2021)
- [The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization](https://mlsanity.com/paper/2202.00443/) (2022)
- [Language Models in the Loop: Incorporating Prompting into Weak Supervision](https://mlsanity.com/paper/2205.02318/) (2022)
- [Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning](https://mlsanity.com/paper/2109.06349/) (2021)
- [Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge](https://mlsanity.com/paper/1608.03000/) (2016)
- [Multi-modal Synthesis of Regular Expressions](https://mlsanity.com/paper/1908.03316/) (2019)
- [TransRegex: Multi-modal Regular Expression Synthesis by Generate-and-Repair](https://mlsanity.com/paper/2012.15489/) (2020)
- [HEIDL: Learning Linguistic Expressions with Deep Learning and Human-in-the-Loop](https://mlsanity.com/paper/1907.11184/) (2019)
- [GrASP: A Library for Extracting and Exploring Human-Interpretable Textual Patterns](https://mlsanity.com/paper/2104.03958/) (2021)

## Abstract (arXiv)

We present RuleChef, a framework that uses large language models (LLMs) to generate executable rules for NLP tasks such as text classification, Named Entity Recognition (NER), or relation extraction. Rules are generated based on a task description and a set of labeled examples, then they are iteratively improved based both on additional examples and on human feedback overexisting rules. RuleChef can also be used to bootstrap rules using the observed input-output pairs from any existing model for a given task. LLMs are used only at learning time, synthesizing rules and iteratively patching them based on failures measured on a held-out split. The result of this process is a fast, deterministic, and inspectable rule system. Preliminary evaluation is performed on both classification and NER tasks. We release RuleChef as open-source software under an Apache 2.0