mlsanityData to 7 Oct 2026

RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules

arXiv 2607.01293 ↗First posted 1 Jul 2026cs.CLcited by 0

Not on the map. Why?

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

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 32 references that are in the map. First posted on arXiv 1 Jul 2026.

Builds on

13 of 32 references.

References · 13

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 710
  3. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 419
  4. 2017Snorkel: Rapid Training Data Creation with Weak Supervisioncited by 370
  5. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
  6. 2022The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymizationcited by 94
  7. 2022Language Models in the Loop: Incorporating Prompting into Weak Supervisioncited by 51
  8. 2021Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuningcited by 46
  9. 2016Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledgecited by 24
  10. 2019Multi-modal Synthesis of Regular Expressionscited by 13
  11. 2020TransRegex: Multi-modal Regular Expression Synthesis by Generate-and-Repaircited by 8
  12. 2019HEIDL: Learning Linguistic Expressions with Deep Learning and Human-in-the-Loopcited by 7
1 more
  1. 2021GrASP: A Library for Extracting and Exploring Human-Interpretable Textual Patternscited by 6

Built on by

Not cited yet.