Using rhetorical strategies to design prompts: a human-in-the-loop approach to make AI useful
Open accessThe DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.
Abstract
The growing capabilities of artificial intelligence (AI) word processing models have demonstrated exceptional potential to impact language related tasks and functions. Their fast pace of adoption and probable effect has also given rise to controversy within certain fields. Models, such as GPT-3, are a particular concern for professionals engaged in writing, particularly as their engagement with these technologies is limited due to lack of ability to control their output. Most efforts to maximize and control output rely on a process known as prompt engineering, the construction and modification of the inputted prompt with expectation for certain outputted or desired text. Consequently, prompt engineering has emerged as an important consideration for research and practice. Previous conceptions of prompt engineering have largely focused on technical and logistic modifications to the back-end processing, remaining inaccessible and, still, limited for most users. In this paper, we look to the technical communication field and its methods of text generation—the rhetorical situation—to conceptualize prompt engineering in a more comprehensible way for its users by considering the context and rhetoric. We introduce a framework, consisting of a formula, to prompt engineering, which demands all components of the rhetorical situation be present in the inputted prompt. We present discussions on the future of AI writing models and their use in both professional and educational settings. Ultimately, this discussion and its findings aim to provide a means of integrating agency and writer-centric methods to AI writing tools to advance a more human-in-the-loop approach. As the use of generative AI and especially NLP-based technologies become common across societal functions, the use of prompt engineering will play a crucial role not just in adoption of the technology, but also its productive and responsible use.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“These generative models are capable of creating text, code, images, and other media at a quality that approaches or rivals human levels, yet they require human intervention to ensure that they are correct with respect to user intent, factual correctness, and ethical appropriateness [31].”
From Human-in-the-Loop Artificial Intelligence: A Systematic Review of Concepts, Methods, and Applications (2026) · cites this paper as [31]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Ranade et al. showed that rhetorical strategies can be applied in a systematic way for prompt engineering, conceptualizing the interaction between humans and AI as a communicative process for which principles of effective discourse are well established [31].”
From Human-in-the-Loop Artificial Intelligence: A Systematic Review of Concepts, Methods, and Applications (2026) · cites this paper as [31]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
GPT-3: Its Nature, Scope, Limits, and Consequences
Floridi, L., & Chiriatti, M. (2020) · Minds and Machines · doi:10.1007/s11023-020-09548-1 · Cited by 2,519 · cited 1×
“This hasn’t changed much since Floridi and Chiriatti (2020) conducted experiments to test AI’s mathematical, semantic and ethical capabilities.”
Making Pre-trained Language Models Better Few-shot Learners
Gao, T., Fisch, A., & Chen, D. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.295 · Cited by 1,380 · cited 1×
“On the other hand, GPT-3 can automatically handle a wide range of tasks with only a few examples by extracting context from natural-language prompts and task demonstrations without many changes to the underlying model (Gao et al. 2020).”
ChatGPT User Experience: Implications for Education
Zhai, X. (2023) · doi:10.2139/ssrn.4312418 · Cited by 935
Virtual reality for collaborative e-learning
Monahan, T., McArdle, G., & Bertolotto, M. (2008) · Computers & Education · doi:10.1016/j.compedu.2006.12.008 · Cited by 435 · cited 1×
“Another category is that of interactive systems— using AR/VR and games as a pedagogical tool for learning and/or as a learning companion is popular (Monahan et al. 2008).”
A Survey on Large Language Models: Applications, Challenges, Limitations, and Practical Usage
Hadi, M. U., tashi, Q. A., Qureshi, R., Shah, A., muneer, A., Irfan, M., Zafar, A., Shaikh, M. B., Akhtar, N., Wu, J., et al. (2023) · doi:10.36227/techrxiv.23589741.v1 · Cited by 370
White, J., Hays, S., Fu, Q., Spencer-Smith, J., & Schmidt, D. C. (2024) · Generative AI for Effective Software Development · doi:10.1007/978-3-031-55642-5_4 · Cited by 295
Short, C. E., & Short, J. C. (2023) · Journal of Business Venturing Insights · doi:10.1016/j.jbvi.2023.e00388 · Cited by 231 · cited 1×
“For example, Short and Short (2023)’s work for generative AI in entrepreneurial communication demonstrates ChatGPT’s ability to mimic each celebrity CEO archetype by prompting language in the style of exemplars.”
A survey of word embeddings based on deep learning
Wang, S., Zhou, W., & Jiang, C. (2020) · Computing · doi:10.1007/s00607-019-00768-7 · Cited by 193
Critical literacy for a posthuman world: When people read, and become, with machines
Leander, K. M., & Burriss, S. K. (2020) · British Journal of Educational Technology · doi:10.1111/bjet.12924 · Cited by 137 · cited 2×
“…studied AI technologies by analyzing algorithmic design and big data perspectives to understand students’ experiences of reading and writing with algorithms, especially with respect to identity, agency, authority, adversary, conversational resource, audience, and so on (Leander and Burriss 2020).”
Towards Tracing Knowledge in Language Models Back to the Training Data
Akyürek, E., Bolukbasi, T., Liu, F., Xiong, B., Tenney, I., Andreas, J., & Guu, K. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.180 · Cited by 137
Surface Form Competition: Why the Highest Probability Answer Isn’t Always Right
Holtzman, A., West, P., Shwartz, V., Choi, Y., & Zettlemoyer, L. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.564 · Cited by 127 · cited 1×
“The solution given by Zhao et al. (2021) and Holtzman et al. (2021) is calibration: adding compensation to the biased tokens so that they are calibrated to an unbiased status.”
Making Pre-trained Language Models Better Few-shot Learners
Gao, T., Fisch, A., & Chen, D. (2020) · arXiv · doi:10.48550/arxiv.2012.15723 · Cited by 124 · cited 1×
“On the other hand, GPT-3 can automatically handle a wide range of tasks with only a few examples by extracting context from natural-language prompts and task demonstrations without many changes to the underlying model (Gao et al. 2020).”
AI & learning: A preferred future
Srinivasan, V. (2022) · Computers and Education Artificial Intelligence · doi:10.1016/j.caeai.2022.100062 · Cited by 123 · cited 1×
“Such applications collect and analyze students’ online learning behavior and performance and provide personal guidance or feedback based on their learning status thus creating an adaptive learning environment (Srinivasan 2022).”
Enhancing adolescent literacy achievement through integration of technology in the classroom
Sternberg, B. J., KAPLAN, K. A., & BORCK, J. E. (2007) · Reading Research Quarterly · doi:10.1598/rrq.42.3.6 · Cited by 86 · cited 1×
“The discussion of writing with AI tools, or assistive writing, has been a popular line of study in literacy which dates as far back as 2007 (Sternberg et al. 2007).”
Intelligent Decision Support Systems
Kaklauskas, A. (2014) · Intelligent systems reference library · doi:10.1007/978-3-319-13659-2_2 · Cited by 67
Chatbot as a New Business Communication Tool: The Case of Naver TalkTalk
Heo, M., & Lee, K. J. (2018) · Business Communication Research and Practice · doi:10.22682/bcrp.2018.1.1.41 · Cited by 51 · cited 2×
“For example, whether we want to write an email or summarize it (Thiergart et al. 2021), or get a suitable response from a chatbot (Heo and Lee 2018)—providing details about what needs to be communicated ( purpose and exigence), who the AI is writing for ( writer ), who will read the output (…”
Ethics for AI Writing: The Importance of Rhetorical Context
McKee, H. A., & Porter, J. E. (2020) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3375627.3375811 · Cited by 51 · cited 1×
“The literature that exists studied generative AI through an analysis of its algorithmic components using computational rhetoric (Hart-Davidson 2018; McKee and Porter 2020; Marcus and Davis 2020).”
Writing with Robots and other Curiosities of the Age of Machine Rhetorics
Hart-Davidson, W. (2018) · Routledge eBooks · doi:10.4324/9781315518497-24 · Cited by 41 · cited 1×
“The literature that exists studied generative AI through an analysis of its algorithmic components using computational rhetoric (Hart-Davidson 2018; McKee and Porter 2020; Marcus and Davis 2020).”
Writing Futures: Collaborative, Algorithmic, Autonomous
Duin, A. H., & Pedersen, I. (2021) · Studies in computational intelligence · doi:10.1007/978-3-030-70928-0 · Cited by 40 · cited 1×
“Duin and Pedersen (2021) come closest to rhetorically evaluating the intelligence of AI writing systems such as GPT-2 and GPT-3.”
Smith, C. R., & Lybarger, S. (1996) · Communication Quarterly · doi:10.1080/01463379609370010 · Cited by 33 · cited 1×
“Smith and Lybarger (1996) also critiqued Bitzer, arguing that “rhetorical situation involves a plurality of exigences and complex relationships between the audience and a rhetorician’s interest”.”
Using Role-Plays to Improve Ethical Understanding of Algorithms Among Computing Students
Hingle, A., Rangwala, H., Johri, A., & Monea, A. (2021) · IEEE Frontiers in Education Conference (FIE) · doi:10.1109/fie49875.2021.9637418 · Cited by 17 · cited 1×
“Other approaches of using AI tools in teaching include developing AI assisted role-playing to help students make ethical decisions (Hingle et al. 2021), enabling collaborations and discussions in classrooms (Miller 2022), peer evaluations in class, reflective assignments to question the AI tool’s…”
Self-citationUnderstanding Emails and Drafting Responses -- An Approach Using GPT-3
Thiergart, J., Huber, S., & Übellacker, T. (2021) · arXiv · doi:10.48550/arxiv.2102.03062 · Cited by 14 · cited 1×
“For example, whether we want to write an email or summarize it (Thiergart et al. 2021), or get a suitable response from a chatbot (Heo and Lee 2018)—providing details about what needs to be communicated ( purpose and exigence), who the AI is writing for ( writer ), who will read the output (…”
McTear, M. (2021) · Synthesis lectures on human language technologies · doi:10.1007/978-3-031-02176-3_1 · Cited by 10
Intelligent Interlocutors in Teaching Language through Distance Learning Education
Руденко-Моргун, О. И., Arkhangelskaya, A. L., & Makarova, N. S. (2022) · CRC Press eBooks · doi:10.1201/9781003184157-10 · Cited by 7
Research works printed but not linked: 10
- Biesecker BA (1989) Rethinking the rhetorical situation from within the thematic of ‘différance.’ Philos Rhetor 22:110–130
- Bitzer LF (1968) The rhetorical situation. Philos Rhetor 1:1–14
- Dhuri U, Jain N (2020) Teaching assessment tool: using AI and secure techniques. Int J Educ Manage Eng 6(08):12–21
- Li C, Zhang M, He Y (2022) The stability-efficiency dilemma: investigating sequence length warmup for training GPT models. Adv Neural Inf Process Syst 35:26736–26750
- Liu Q, Kusner MJ, Blunsom P (2020) A survey on contextual embeddings. Preprint at arXiv:2003.07278 · arXiv
- Liu P, Yuan W, Fu J, Jiang Z, Hayashi H, Neubig G (2021) Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. Preprint at http://arxiv.org/abs/2107.13586 · arXiv
- Marcus G, Davis E (2020) GPT-3, Bloviator: OpenAI’s language generator has no idea what it’s talking about. Technology Review
- Smith TS (2008) What connection does rhetorical theory have to technical and professional communication? In: MacLennan J (ed) Readings for technical communication. Oxford University Press Canada, Don Mills, ON, Canada, pp 114–120
- Vatz RE (1973) The myth of the rhetorical situation. Philos Rhetor 6:154–161
- Zhao Z, Wallace E, Feng S, Klein D, Singh S (2021, July) Calibrate before use: improving few-shot performance of language models. In: International conference on machine learning, pp 12697–12706 PMLR
Cited by
Leveraging generative AI for course learning outcome categorization using Bloom's taxonomy
Almatrafi, O., & Johri, A. (2025) · Computers and Education Artificial Intelligence · doi:10.1016/j.caeai.2025.100404 · Cited by 55
Self-citationLazaros, K., Vrahatis, A. G., & Kotsiantis, S. (2026) · Entropy · doi:10.3390/e28040377 · Cited by 50
Johri, A., Hingle, A., & Schleiß, J. (2024) · IEEE Frontiers in Education Conference (FIE) · doi:10.1109/fie61694.2024.10893017 · Cited by 37
Self-citationGupta, A., & Shivers-McNair, A. (2024) · Computers & composition/Computers and composition · doi:10.1016/j.compcom.2024.102882 · Cited by 33
Getto, G., Kelley, S., & Vance, B. (2025) · Journal of Technical Writing and Communication · doi:10.1177/00472816251332208 · Cited by 30
“Ranade et (2024) examined how rhetorically-informed prompt design is an essential skill that is critical to ensuring AI outputs align accurately with human intentions.”
Influential
Metadata
- Authors
- Ranade, N., Saravia, M., & Johri, A.
- Affiliations
- George Mason University (US)
- Corresponding author
- Ranade, Nupoor
- Venue
- AI & SOCIETY
- Published
- 2024-04-01
- Volume
- 40
- Issue
- 2
- Pages
- 711-732
- ISSN
- 0951-5666 (ISSN-L)
- 1435-5655
- OpenAlex
- W4393381464
- Cited by
- 53
- References
- 22
- Citations by year
- 2026: 31 · 2025: 18 · 2024: 4
- FWCI
- 7.85
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- AI & Society (publishedVersion, cc-by)
- Funders
- National Science Foundation (204863, 1937950, 1939105)
- Office of the Provost and Executive Vice President, George Mason University
- National Institute of Food and Agriculture (2021-67021-35329)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- prompt engineering, rhetorical situation, human-in-the-loop, generative AI, AI writing tools, technical communication, GPT-3, writer agency, responsible AI use
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.


