Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools

TL;DR

Thermostat provides a comprehensive, open-source collection of over 200,000 NLP model explanations and analysis tools, significantly easing research and comparison of explainability methods across models and datasets.

Contribution

It introduces a large, publicly available dataset of NLP model explanations and versatile tools for analysis, saving extensive computational resources and promoting reproducibility.

Findings

Enables detailed analysis of NLP model explanations

Facilitates comparison across models and datasets

Reduces redundant computational efforts

Abstract

In the language domain, as in other domains, neural explainability takes an ever more important role, with feature attribution methods on the forefront. Many such methods require considerable computational resources and expert knowledge about implementation details and parameter choices. To facilitate research, we present Thermostat which consists of a large collection of model explanations and accompanying analysis tools. Thermostat allows easy access to over 200k explanations for the decisions of prominent state-of-the-art models spanning across different NLP tasks, generated with multiple explainers. The dataset took over 10k GPU hours (> one year) to compile; compute time that the community now saves. The accompanying software tools allow to analyse explanations instance-wise but also accumulatively on corpus level. Users can investigate and compare models, datasets and explainers without the need to orchestrate implementation details. Thermostat is fully open source, democratizes explainability research in the language domain, circumvents redundant computations and increases comparability and replicability.