ICX360: In-Context eXplainability 360 Toolkit
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914157796786176 |
|---|---|
| author | Wei, Dennis Luss, Ronny Hu, Xiaomeng Paes, Lucas Monteiro Chen, Pin-Yu Ramamurthy, Karthikeyan Natesan Miehling, Erik Vejsbjerg, Inge Strobelt, Hendrik |
| author_facet | Wei, Dennis Luss, Ronny Hu, Xiaomeng Paes, Lucas Monteiro Chen, Pin-Yu Ramamurthy, Karthikeyan Natesan Miehling, Erik Vejsbjerg, Inge Strobelt, Hendrik |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_10879 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ICX360: In-Context eXplainability 360 Toolkit Wei, Dennis Luss, Ronny Hu, Xiaomeng Paes, Lucas Monteiro Chen, Pin-Yu Ramamurthy, Karthikeyan Natesan Miehling, Erik Vejsbjerg, Inge Strobelt, Hendrik Computation and Language Machine Learning 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. |
| title | ICX360: In-Context eXplainability 360 Toolkit |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2511.10879 |