paper-with-me

Papers

Interactive Prompt Debugging with Sequence Salience

2024-04-11 · Ian Tenney, Ryan Mullins, Bin Du, Shree Pandya, Minsuk Kahng, Lucas Dixon

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.

📄 PDF Abstract BibTeX arXiv:2404.07498

Code (1)

PAIR-code/lit 공식 구현 pytorch

Tasks

Sentencetext-classificationText Classification

Similar Papers 제목 키워드 기반

LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models

2022-04-26 · Mor Geva, Avi Caciularu, Guy Dar, Paul Roit 외

The opaque nature and unexplained behavior of transformer-based language models (LMs) have spurred a wide interest in interpreting their predictions. However, current interpretation methods mostly focus on probing models…

Prediction

Interactive Debugging and Steering of Multi-Agent AI Systems

2025-03-03 · Will Epperson, Gagan Bansal, Victor Dibia, Adam Fourney 외

Fully autonomous teams of LLM-powered AI agents are emerging that collaborate to perform complex tasks for users. What challenges do developers face when trying to build and debug these AI agent teams? In formative inter…

AI Agent

debug-gym: A Text-Based Environment for Interactive Debugging

2025-03-27 · Xingdi Yuan, Morgane M Moss, Charbel El Feghali, Chinmay Singh 외

Large Language Models (LLMs) are increasingly relied upon for coding tasks, yet in most scenarios it is assumed that all relevant information can be either accessed in context or matches their training data. We posit tha…

Interactive Visualization for Debugging RL

2020-08-14 · Shuby Deshpande, Benjamin Eysenbach, Jeff Schneider

Visualization tools for supervised learning allow users to interpret, introspect, and gain an intuition for the successes and failures of their models. While reinforcement learning practitioners ask many of the same ques…

AgentStepper: Interactive Debugging of Software Development Agents

2026-02-06 · Robert Hutter, Michael Pradel arxiv

Software development agents powered by large language models (LLMs) have shown great promise in automating tasks like environment setup, issue solving, and program repair. Unfortunately, understanding and debugging such …

Program Repair