Towards Dataset-scale and Feature-oriented Evaluation of Text Summarization in Large Language Model Prompts

TL;DR

This paper proposes a feature-oriented evaluation workflow and a visual analytics system, Awesum, to systematically assess and refine text summarization prompts for large language models, emphasizing interpretability and user-friendliness.

Contribution

It introduces a novel feature-based prompt evaluation approach and the Awesum system, facilitating non-technical users to effectively optimize prompts at dataset scale.

Findings

The system helps non-technical users evaluate prompts more easily.

Feature-oriented evaluation can generalize beyond text summarization.

The workflow improves prompt refinement efficiency.

Abstract

Recent advancements in Large Language Models (LLMs) and Prompt Engineering have made chatbot customization more accessible, significantly reducing barriers to tasks that previously required programming skills. However, prompt evaluation, especially at the dataset scale, remains complex due to the need to assess prompts across thousands of test instances within a dataset. Our study, based on a comprehensive literature review and pilot study, summarized five critical challenges in prompt evaluation. In response, we introduce a feature-oriented workflow for systematic prompt evaluation. In the context of text summarization, our workflow advocates evaluation with summary characteristics (feature metrics) such as complexity, formality, or naturalness, instead of using traditional quality metrics like ROUGE. This design choice enables a more user-friendly evaluation of prompts, as it guides users in sorting through the ambiguity inherent in natural language. To support this workflow, we introduce Awesum, a visual analytics system that facilitates identifying optimal prompt refinements for text summarization through interactive visualizations, featuring a novel Prompt Comparator design that employs a BubbleSet-inspired design enhanced by dimensionality reduction techniques. We evaluate the effectiveness and general applicability of the system with practitioners from various domains and found that (1) our design helps overcome the learning curve for non-technical people to conduct a systematic evaluation of summarization prompts, and (2) our feature-oriented workflow has the potential to generalize to other NLG and image-generation tasks. For future works, we advocate moving towards feature-oriented evaluation of LLM prompts and discuss unsolved challenges in terms of human-agent interaction.