LLM Attributor: Interactive Visual Attribution for LLM Generation

arXiv:2404.01361v1 Announce Type: cross
Abstract: 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 …

arxiv attribution cs.ai cs.cl cs.hc cs.lg interactive llm type visual