# Exemplar Auditing for Multi-Label Biomedical Text Classification

arXiv: https://arxiv.org/abs/2004.03093 · HTML: https://mlsanity.com/paper/2004.03093/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2020.

## Built on by (most cited first, 2 of 2)

- [Data-to-text Generation by Splicing Together Nearest Neighbors](https://mlsanity.com/paper/2101.08248/) (2021)
- [Approximate Conditional Coverage & Calibration via Neural Model Approximations](https://mlsanity.com/paper/2205.14310/) (2022)

## Abstract (arXiv)

Many practical applications of AI in medicine consist of semi-supervised discovery: The investigator aims to identify features of interest at a resolution more fine-grained than that of the available human labels. This is often the scenario faced in healthcare applications as coarse, high-level labels (e.g., billing codes) are often the only sources that are readily available. These challenges are compounded for modalities such as text, where the feature space is very high-dimensional, and often contains considerable amounts of noise. In this work, we generalize a recently proposed zero-shot sequence labeling method, "binary labeling via a convolutional decomposition", to the case where the available document-level human labels are themselves relatively high-dimensional. The approach yields classification with "introspection", relating the fine-grained features of an inference-time prediction to their nearest neighbors from the training set, under the model. The approach is effective, yet parsimonious, as demonstrated on a well-studied MIMIC-III multi-label classification task of electronic health record data, and is useful as a tool for organizing the analysis of neural model predictions and high-dimensional datasets. Our proposed approach yields both a competitively effective classification model and an interrogation mechanism to aid healthcare workers in understanding the salient features that drive the model's predictions.