# How You Prompt Matters! Even Task-Oriented Constraints in Instructions Affect LLM-Generated Text Detection

arXiv: https://arxiv.org/abs/2311.08369 · HTML: https://mlsanity.com/paper/2311.08369/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 45 references that are in the map.
- First posted on arXiv 14 Nov 2023.

## Builds on (most cited first, 19 of 19)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [Benchmarking Large Language Models for News Summarization](https://mlsanity.com/paper/2301.13848/) (2023)
- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [Prompting Large Language Model for Machine Translation: A Case Study](https://mlsanity.com/paper/2301.07069/) (2023)
- [Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders](https://mlsanity.com/paper/1703.10960/) (2017)
- [DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2306.05540/) (2023)
- [The Science of Detecting LLM-Generated Texts](https://mlsanity.com/paper/2303.07205/) (2023)
- [ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine Learning Model for Detecting Short ChatGPT-generated Text](https://mlsanity.com/paper/2301.13852/) (2023)
- [OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples](https://mlsanity.com/paper/2307.11729/) (2023)
- [ArguGPT: evaluating, understanding and identifying argumentative essays generated by GPT models](https://mlsanity.com/paper/2304.07666/) (2023)

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

- [RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors](https://mlsanity.com/paper/2405.07940/) (2024)
- [Spotting AI's Touch: Identifying LLM-Paraphrased Spans in Text](https://mlsanity.com/paper/2405.12689/) (2024)
- [HACo-Det: A Study Towards Fine-Grained Machine-Generated Text Detection under Human-AI Coauthoring](https://mlsanity.com/paper/2506.02959/) (2025)
- [GenAI Content Detection Task 3: Cross-Domain Machine-Generated Text Detection Challenge](https://mlsanity.com/paper/2501.08913/) (2025)
- [How Sampling Affects the Detectability of Machine-written texts: A Comprehensive Study](https://mlsanity.com/paper/2510.13681/) (2025)
- [Investigating the Influence of Prompt-Specific Shortcuts in AI Generated Text Detection](https://mlsanity.com/paper/2406.16275/) (2024)
- [Balanced Multi-Factor In-Context Learning for Multilingual Large Language Models](https://mlsanity.com/paper/2502.11495/) (2025)
- [How Much Were You Told? Measuring External Information in Peer Reviews](https://mlsanity.com/paper/2609.28041/) (2026)

## Abstract (arXiv)

To combat the misuse of Large Language Models (LLMs), many recent studies have presented LLM-generated-text detectors with promising performance. When users instruct LLMs to generate texts, the instruction can include different constraints depending on the user's need. However, most recent studies do not cover such diverse instruction patterns when creating datasets for LLM detection. In this paper, we reveal that even task-oriented constraints -- constraints that would naturally be included in an instruction and are not related to detection-evasion -- cause existing powerful detectors to have a large variance in detection performance. We focus on student essay writing as a realistic domain and manually create task-oriented constraints based on several factors for essay quality. Our experiments show that the standard deviation (SD) of current detector performance on texts generated by an instruction with such a constraint is significantly larger (up to an SD of 14.4 F1-score) than that by generating texts multiple times or paraphrasing the instruction. We also observe an overall trend where the constraints can make LLM detection more challenging than without them. Finally, our analysis indicates that the high instruction-following ability of LLMs fosters the large impact of such constraints on detection performance.