LLM Attributor: Interactive Visual Attribution for LLM Generation

While large language models (LLMs) have shown remarkable capability to generate convincing text across diverse domains, concerns around its potential risks have highlighted the importance of understanding the rationale behind text generation. We present LLM ATTRIBUTOR, a Python library that provides interactive visualizations for training data attribution of an LLM’s text generation. Our library offers a new way to quickly attribute an LLM’s text generation to training data points to inspect model behaviors, enhance its trustworthiness, and compare model-generated text with user-provided text. Thanks to LLM ATTRIBUTOR’s broad support for computational notebooks, users can easily integrate it into their workflow to interactively visualize attributions of their models.

Authors

• Seongmin Lee Georgia Tech
• Zijie J. Wang Georgia Tech
• Aishwarya Chakravarthy Georgia Tech
• Alec Helbling Georgia Tech
• ShengYun Peng Georgia Tech
• Mansi Phute Georgia Tech
• Duen Horng (Polo) Chau Georgia Tech
• Minsuk Kahng Google Research

Keywords

No keywords are indexed for this paper.