Interactive Prompt Debugging with Sequence Salience

We present Sequence Salience, a visual tool for interactive prompt debugging with input salience methods. Sequence Salience builds on widely used salience methods for text classification and single-token prediction, and extends this to a system tailored for debugging complex LLM prompts. Our system...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Tenney, Ian, Mullins, Ryan, Du, Bin, Pandya, Shree, Kahng, Minsuk, Dixon, Lucas
Format Paper Journal Article
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 11.04.2024
Subjects
Computer Science - Artificial Intelligence
Computer Science - Computation and Language
Computer Science - Human-Computer Interaction
Computer Science - Learning
Controllability
Debugging
Salience
Online AccessGet full text

Cover

More Information
Summary:We present Sequence Salience, a visual tool for interactive prompt debugging with input salience methods. Sequence Salience builds on widely used salience methods for text classification and single-token prediction, and extends this to a system tailored for debugging complex LLM prompts. Our system is well-suited for long texts, and expands on previous work by 1) providing controllable aggregation of token-level salience to the word, sentence, or paragraph level, making salience over long inputs tractable; and 2) supporting rapid iteration where practitioners can act on salience results, refine prompts, and run salience on the new output. We include case studies showing how Sequence Salience can help practitioners work with several complex prompting strategies, including few-shot, chain-of-thought, and constitutional principles. Sequence Salience is built on the Learning Interpretability Tool, an open-source platform for ML model visualizations, and code, notebooks, and tutorials are available at http://goo.gle/sequence-salience.
ISSN:2331-8422
DOI:10.48550/arxiv.2404.07498