OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models
This addresses the challenge for users of tracking goal progress in complex LLM dialogues, offering incremental improvements to existing chat interfaces.
The paper tackles the problem of users managing conversational goals in multi-turn dialogues with large language models (LLMs) by introducing OnGoal, an interface that provides real-time feedback and visualizations. In a study with 20 participants, using OnGoal reduced time and effort to achieve goals while encouraging exploration of new prompting strategies.
As multi-turn dialogues with large language models (LLMs) grow longer and more complex, how can users better evaluate and review progress on their conversational goals? We present OnGoal, an LLM chat interface that helps users better manage goal progress. OnGoal provides real-time feedback on goal alignment through LLM-assisted evaluation, explanations for evaluation results with examples, and overviews of goal progression over time, enabling users to navigate complex dialogues more effectively. Through a study with 20 participants on a writing task, we evaluate OnGoal against a baseline chat interface without goal tracking. Using OnGoal, participants spent less time and effort to achieve their goals while exploring new prompting strategies to overcome miscommunication, suggesting tracking and visualizing goals can enhance engagement and resilience in LLM dialogues. Our findings inspired design implications for future LLM chat interfaces that improve goal communication, reduce cognitive load, enhance interactivity, and enable feedback to improve LLM performance.