OpenAutoNLU: Open Source AutoML Library for NLU

Grigory Arshinov; Aleksandr Boriskin; Sergey Senichev; Ayaz Zaripov; Daria Galimzianova; Daniil Karpov; Leonid Sanochkin

Paper · arXiv 2603.01824

OpenAutoNLU: Open Source AutoML Library for NLU

Grigory Arshinov, Aleksandr Boriskin, Sergey Senichev, Ayaz Zaripov, Daria Galimzianova, Daniil Karpov, Leonid Sanochkin

50 upvotesMarch 2, 2026arXiv 预印本

AI 摘要

OpenAutoNLU is an open-source automated machine learning library for NLU tasks that employs data-aware training selection and includes integrated diagnostics and LLM features through a minimal low-code interface.

automated machine learningnatural language understandingtext classificationnamed entity recognitiondata-aware training regime selectiondata quality diagnosticsout-of-distribution detectionlarge language models

Abstract

OpenAutoNLU is an open-source automated machine learning library for natural language understanding (NLU) tasks, covering both text classification and named entity recognition (NER). Unlike existing solutions, we introduce data-aware training regime selection that requires no manual configuration from the user. The library also provides integrated data quality diagnostics, configurable out-of-distribution (OOD) detection, and large language model (LLM) features, all within a minimal lowcode API. The demo app is accessible here https://openautonlu.dev.