EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria

Abstract

By simply composing prompts, developers can prototype novel generative applications with Large Language Models (LLMs). To refine prototypes into products, however, developers must iteratively revise prompts by evaluating outputs to diagnose weaknesses. Formative interviews (N=8) revealed that developers invest significant effort in manually evaluating outputs as they assess context-specific and subjective criteria. We present EvalLM, an interactive system for iteratively refining prompts by evaluating multiple outputs on user-defined criteria. By describing criteria in natural language, users can employ the system's LLM-based evaluator to get an overview of where prompts excel or fail, and improve these based on the evaluator's feedback. A comparative study (N=12) showed that EvalLM, when compared to manual evaluation, helped participants compose more diverse criteria, examine twice as many outputs, and reach satisfactory prompts with 59% fewer revisions. Beyond prompts, our work can be extended to augment model evaluation and alignment in specific application contexts.

Accepted to CHI 2024

References in corpus (7)

• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• Out of One, Many: Using Language Models to Simulate Human Samples
• "What It Wants Me To Say": Bridging the Abstraction Gap Between End-User Programmers and Code-Generating Large Language Models
• Discovering and Validating AI Errors With Crowdsourced Failure Reports
• Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning
• ScatterShot: Interactive In-context Example Curation for Text Transformation
• Angler: Helping Machine Translation Practitioners Prioritize Model Improvements

Cited by in corpus (11)

• What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Use
• Interactive Debugging and Steering of Multi-Agent AI Systems
• Towards Dataset-scale and Feature-oriented Evaluation of Text Summarization in Large Language Model Prompts
• ChainBuddy: An AI Agent System for Generating LLM Pipelines
• Gensors: Authoring Personalized Visual Sensors with Multimodal Foundation Models and Reasoning
• RAGTrace: Understanding and Refining Retrieval-Generation Dynamics in Retrieval-Augmented Generation
• Vipera: Towards systematic auditing of generative text-to-image models at scale
• Policy Maps: Tools for Guiding the Unbounded Space of LLM Behaviors
• DxHF: Providing High-Quality Human Feedback for LLM Alignment via Interactive Decomposition
• Visual Text Mining with Progressive Taxonomy Construction for Environmental Studies
• OOPrompt: Reifying Intents into Structured Artifacts for Modular and Iterative Prompting