Prompting in the Dark: Assessing Human Performance in Prompt Engineering for Data Labeling When Gold Labels Are Absent

Abstract

Millions of users prompt large language models (LLMs) for various tasks, but how good are people at prompt engineering? Do users actually get closer to their desired outcome over multiple iterations of their prompts? These questions are crucial when no gold-standard labels are available to measure progress. This paper investigates a scenario in LLM-powered data labeling, "prompting in the dark," where users iteratively prompt LLMs to label data without using manually-labeled benchmarks. We developed PromptingSheet, a Google Sheets add-on that enables users to compose, revise, and iteratively label data through spreadsheets. Through a study with 20 participants, we found that prompting in the dark was highly unreliable -- only 9 participants improved labeling accuracy after four or more iterations. Automated prompt optimization tools like DSPy also struggled when few gold labels were available. Our findings highlight the importance of gold labels and the needs, as well as the risks, of automated support in human prompt engineering, providing insights for future tool design.

Accepted By CHI 2025

References in corpus (6)

• To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making
• ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing
• If in a Crowdsourced Data Annotation Pipeline, a GPT-4
• Harnessing LLMs for Automated Video Content Analysis: An Exploratory Workflow of Short Videos on Depression
• Improving Text-to-Image Consistency via Automatic Prompt Optimization
• Clarify: Improving Model Robustness With Natural Language Corrections