# Are Good Explainers Secretly Human-in-the-Loop Active Learners?

arXiv: https://arxiv.org/abs/2306.13935 · HTML: https://mlsanity.com/paper/2306.13935/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 24 Jun 2023.

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

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Universal Sentence Encoder](https://mlsanity.com/paper/1803.11175/) (2018)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Tune: A Research Platform for Distributed Model Selection and Training](https://mlsanity.com/paper/1807.05118/) (2018)
- [Reliable Post hoc Explanations: Modeling Uncertainty in Explainability](https://mlsanity.com/paper/2008.05030/) (2020)
- [Diverse mini-batch Active Learning](https://mlsanity.com/paper/1901.05954/) (2019)
- [Interpretation of NLP models through input marginalization](https://mlsanity.com/paper/2010.13984/) (2020)
- [modAL: A modular active learning framework for Python](https://mlsanity.com/paper/1805.00979/) (2018)
- [Deep Active Learning for Text Classification with Diverse Interpretations](https://mlsanity.com/paper/2108.10687/) (2021)

## Built on by (most cited first, 1 of 1)

- [On the Fragility of Active Learners for Text Classification](https://mlsanity.com/paper/2403.15744/) (2024)

## Abstract (arXiv)

Explainable AI (XAI) techniques have become popular for multiple use-cases in the past few years. Here we consider its use in studying model predictions to gather additional training data. We argue that this is equivalent to Active Learning, where the query strategy involves a human-in-the-loop. We provide a mathematical approximation for the role of the human, and present a general formalization of the end-to-end workflow. This enables us to rigorously compare this use with standard Active Learning algorithms, while allowing for extensions to the workflow. An added benefit is that their utility can be assessed via simulation instead of conducting expensive user-studies. We also present some initial promising results.