ICX360: In-Context eXplainability 360 Toolkit
This toolkit addresses the need for explainability in LLMs for users in high-stakes applications, but it is incremental as it packages existing methods into a unified framework.
The authors introduced ICX360, an open-source Python toolkit for explaining large language models (LLMs) by focusing on user-provided context, implementing three recent tools using black-box and white-box methods.
Large Language Models (LLMs) have become ubiquitous in everyday life and are entering higher-stakes applications ranging from summarizing meeting transcripts to answering doctors' questions. As was the case with earlier predictive models, it is crucial that we develop tools for explaining the output of LLMs, be it a summary, list, response to a question, etc. With these needs in mind, we introduce In-Context Explainability 360 (ICX360), an open-source Python toolkit for explaining LLMs with a focus on the user-provided context (or prompts in general) that are fed to the LLMs. ICX360 contains implementations for three recent tools that explain LLMs using both black-box and white-box methods (via perturbations and gradients respectively). The toolkit, available at https://github.com/IBM/ICX360, contains quick-start guidance materials as well as detailed tutorials covering use cases such as retrieval augmented generation, natural language generation, and jailbreaking.