generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation

arXiv:2403.07627v1 Announce Type: cross
Abstract: Large language models (LLMs) are widely deployed in various downstream tasks, e.g., auto-completion, aided writing, or chat-based text generation. However, the considered output candidates of the underlying search algorithm are under-explored and under-explained. We tackle this shortcoming by proposing a tree-in-the-loop approach, where a visual representation of the beam search tree is the central component for analyzing, explaining, and adapting the generated outputs. To support these tasks, we present generAItor, a visual analytics technique, augmenting …

abstract algorithm arxiv auto chat cs.hc cs.lg explainability explained however language language model language models large language large language models llms loop search tasks text text generation tree type visual writing