# From Prompt Engineering to Prompt Science With Human in the Loop

arXiv: https://arxiv.org/abs/2401.04122 · HTML: https://mlsanity.com/paper/2401.04122/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 56 references that are in the map.
- First posted on arXiv 1 Jan 2024.

## Builds on (most cited first, 18 of 18)

- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [A Survey of Hallucination in Large Foundation Models](https://mlsanity.com/paper/2309.05922/) (2023)
- [LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2304.01933/) (2023)
- [Can Large Language Models Transform Computational Social Science?](https://mlsanity.com/paper/2305.03514/) (2023)
- [Auditing large language models: a three-layered approach](https://mlsanity.com/paper/2302.08500/) (2023)
- [Large language models can accurately predict searcher preferences](https://mlsanity.com/paper/2309.10621/) (2023)
- [A Confederacy of Models: a Comprehensive Evaluation of LLMs on Creative Writing](https://mlsanity.com/paper/2310.08433/) (2023)
- [GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problems](https://mlsanity.com/paper/2310.12397/) (2023)
- [Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models](https://mlsanity.com/paper/2208.07852/) (2022)
- [LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Coding](https://mlsanity.com/paper/2306.14924/) (2023)
- [Prompt Engineering a Prompt Engineer](https://mlsanity.com/paper/2311.05661/) (2023)
- [Supporting Human-AI Collaboration in Auditing LLMs with LLMs](https://mlsanity.com/paper/2304.09991/) (2023)
- [Efficiently Leveraging Multi-level User Intent for Session-based Recommendation via Atten-Mixer Network](https://mlsanity.com/paper/2206.12781/) (2022)
- [Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomies](https://mlsanity.com/paper/2309.13063/) (2023)
- [Prompting or Fine-tuning? A Comparative Study of Large Language Models for Taxonomy Construction](https://mlsanity.com/paper/2309.01715/) (2023)
- [Shaping the Emerging Norms of Using Large Language Models in Social Computing Research](https://mlsanity.com/paper/2307.04280/) (2023)
- [Taking Search to Task](https://mlsanity.com/paper/2301.05046/) (2023)

## Built on by (most cited first, 12 of 12)

- [AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities](https://mlsanity.com/paper/2508.11126/) (2025)
- [AuditLLM: A Tool for Auditing Large Language Models Using Multiprobe Approach](https://mlsanity.com/paper/2402.09334/) (2024)
- [LLMAuditor: A Framework for Auditing Large Language Models Using Human-in-the-Loop](https://mlsanity.com/paper/2402.09346/) (2024)
- [Which Words Matter Most in Zero-Shot Prompts?](https://mlsanity.com/paper/2502.03418/) (2025)
- [Prompting as Scientific Inquiry](https://mlsanity.com/paper/2507.00163/) (2025)
- [Generative Artificial Intelligence in Qualitative Research Methods: Between Hype and Risks?](https://mlsanity.com/paper/2511.08461/) (2025)
- [Whose Name Comes Up? II: Benchmarking and Intervention-Based Auditing of LLM-Based Scholar Recommendation](https://mlsanity.com/paper/2602.08873/) (2026)
- [Key Considerations for Domain Expert Involvement in LLM Design and Evaluation: An Ethnographic Study](https://mlsanity.com/paper/2602.14357/) (2026)
- [JMMMU-Pro: Image-based Japanese Multi-discipline Multimodal Understanding Benchmark via Vibe Benchmark Construction](https://mlsanity.com/paper/2512.14620/) (2025)
- [When in Doubt, Consult: Expert Debate for Sexism Detection via Confidence-Based Routing](https://mlsanity.com/paper/2512.23732/) (2025)
- [Leveraging LLMs for Grammar Adaptation: A Study on Metamodel-Grammar Co-Evolution](https://mlsanity.com/paper/2605.21465/) (2026)
- [CogniConsole: Externalizing Inference-Time Control as a Formal Abstraction for Reliable LLM Interactions](https://mlsanity.com/paper/2607.08774/) (2026)

## Abstract (arXiv)

As LLMs make their way into many aspects of our lives, one place that warrants increased scrutiny with LLM usage is scientific research. Using LLMs for generating or analyzing data for research purposes is gaining popularity. But when such application is marred with ad-hoc decisions and engineering solutions, we need to be concerned about how it may affect that research, its findings, or any future works based on that research. We need a more scientific approach to using LLMs in our research. While there are several active efforts to support more systematic construction of prompts, they are often focused more on achieving desirable outcomes rather than producing replicable and generalizable knowledge with sufficient transparency, objectivity, or rigor. This article presents a new methodology inspired by codebook construction through qualitative methods to address that. Using humans in the loop and a multi-phase verification processes, this methodology lays a foundation for more systematic, objective, and trustworthy way of applying LLMs for analyzing data. Specifically, we show how a set of researchers can work through a rigorous process of labeling, deliberating, and documenting to remove subjectivity and bring transparency and replicability to prompt generation process. A set of experiments are presented to show how this methodology can be put in practice.