# CoPrompter: User-Centric Evaluation of LLM Instruction Alignment for Improved Prompt Engineering

arXiv: https://arxiv.org/abs/2411.06099 · HTML: https://mlsanity.com/paper/2411.06099/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2024.

## Built on by (most cited first, 8 of 8)

- [Literature-Grounded Novelty Assessment of Scientific Ideas](https://mlsanity.com/paper/2506.22026/) (2025)
- [Prompting in the Dark: Assessing Human Performance in Prompt Engineering for Data Labeling When Gold Labels Are Absent](https://mlsanity.com/paper/2502.11267/) (2025)
- [Incident Analysis for AI Agents](https://mlsanity.com/paper/2508.14231/) (2025)
- [AttackSeqBench: Benchmarking the Capabilities of LLMs for Attack Sequences Understanding](https://mlsanity.com/paper/2503.03170/) (2025)
- [Security Steerability is All You Need](https://mlsanity.com/paper/2504.19521/) (2025)
- [Understanding Prompt Programming Tasks and Questions](https://mlsanity.com/paper/2507.17264/) (2025)
- [Intentmaking and Sensemaking: Human Interaction with AI-Guided Mathematical Discovery](https://mlsanity.com/paper/2605.05921/) (2026)
- [PromptPilot: Improving Human-AI Collaboration Through LLM-Enhanced Prompt Engineering](https://mlsanity.com/paper/2510.00555/) (2025)

## Abstract (arXiv)

Ensuring large language models' (LLMs) responses align with prompt instructions is crucial for application development. Based on our formative study with industry professionals, the alignment requires heavy human involvement and tedious trial-and-error especially when there are many instructions in the prompt. To address these challenges, we introduce CoPrompter, a framework that identifies misalignment based on assessing multiple LLM responses with criteria. It proposes a method to generate evaluation criteria questions derived directly from prompt requirements and an interface to turn these questions into a user-editable checklist. Our user study with industry prompt engineers shows that CoPrompter improves the ability to identify and refine instruction alignment with prompt requirements over traditional methods, helps them understand where and how frequently models fail to follow user's prompt requirements, and helps in clarifying their own requirements, giving them greater control over the response evaluation process. We also present the design lessons to underscore our system's potential to streamline the prompt engineering process.