The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models

By Ian Tenney, James Wexler, Jasmijn Bastings, Tolga Bolukbasi, Andy Coenen, Sebastian Gehrmann, Ellen Jiang, Mahima Pushkarna, Carey Radebaugh, Emily Reif and 1 more. 2020

224 citations recorded by the source corpus.

We present the Language Interpretability Tool (LIT), an open-source platform for visualization and understanding of NLP models. We focus on core questions about model behavior: Why did my model make this prediction? When does it perform poorly? What happens under a controlled change in the input? LIT integrates local explanations, aggregate analysis, and counterfactual generation into a streamlined, browser-based interface to enable rapid exploration and error analysis. We include case studies for a diverse set of workflows, including exploring counterfactuals for sentiment analysis, measuring gender bias in coreference systems, and exploring local behavior in text generation. LIT supports a wide range of models—including classification, seq2seq, and structured prediction—and is highly extensible through a declarative, framework-agnostic API. LIT is under active development, with code and full documentation available at https://github.com/pair-code/lit.

Subfields: Artificial Intelligence, Natural Language Processing, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Safety, Robustness & Interpretability

Citations in the corpus

Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text (2022, neutral): “For example, the the Language Interpretability Tool (Tenney et al., 2020) can automatically evaluate on subpopulations, and Explainaboard (Liu et al.”
ExplainaBoard: An Explainable Leaderboard for NLP (2021, background): “On the other hand, there are many other glass-box interpretability tools that look at model internals, such as the AllenNLP Interpret (Wallace et al., 2019) and Language Inter-pretability Tool (Tenney et al., 2020).”
Gemma 2: Improving Open Language Models at a Practical Size (2024, methodology): “Additionally, the toolkit includes a methodology to build customized classifiers with Gemma using a limited number of datapoints thanks to parameter efficient tuning techniques (Mozes et al., 2023) , an interactive prompt-debugging platform, based on top of the Learning Interpretability Tool (Tenney”
Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making (2021, background): “[61] develop an interative interpretability tool that provide insightful visualizations for NLP tasks.”
Robustness Gym: Unifying the NLP Evaluation Landscape (2021, methodology): “Tools include the recent Language Interpretability Tool (LIT) (Tenney et al., 2020), IBM’s AI Explainability 360 (Arya et al.”
Automatic Construction of Evaluation Suites for Natural Language Generation Datasets (2021, unknown): “Another approach is to delegate the slicing agency to those working with a dataset through interactive systems like Errudite [22] or the Language Interpretability Tool [23].”
Post-hoc Interpretability for Neural NLP: A Survey (2021, background): “We suspect a reason for primarily explaining sequence-to-class models, is that sequence-to-sequence explanations may depend on interactive visualization to a greater extent [72, 111, 117], which is harder to implement and write about in typical machine learning venues.”
Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision (2020, background): “There is growing interest in NLP in opening the black-box, through surrogate models (Ribeiro, Singh, and Guestrin 2016), counterfactual evaluation (Tenney et al. 2020), examining the inner structure of the neural network (Raffel et al.”