arxiv: 2302.11382 · v1 · submitted 2023-02-21 · 💻 cs.SE · cs.AI

Recognition: 2 theorem links

· Lean Theorem

A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT

Jules White , Quchen Fu , Sam Hays , Michael Sandborn , Carlos Olea , Henry Gilbert , Ashraf Elnashar , Jesse Spencer-Smith

show 1 more author

Douglas C. Schmidt

Authors on Pith no claims yet

Pith reviewed 2026-05-15 07:04 UTC · model grok-4.3

classification 💻 cs.SE cs.AI

keywords prompt engineeringprompt patternslarge language modelsChatGPTsoftware patternsLLM interactionsprompt catalog

0 comments

The pith

A catalog of prompt patterns provides reusable solutions to common problems in LLM conversations.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper offers a framework for documenting prompt engineering techniques as patterns. It presents a catalog of patterns that have successfully improved outputs from models like ChatGPT. These patterns help enforce rules and automate processes in prompt design. The work also shows how to combine patterns for more sophisticated interactions. This approach treats prompts as a form of programming for customizing LLM behavior.

Core claim

The central claim is that prompt patterns act as reusable solutions to common problems in output generation and interaction with large language models, allowing for systematic improvement in prompt engineering through a documented catalog that can be adapted across domains.

What carries the argument

The prompt pattern, defined as a structured template providing reusable solutions to problems in LLM prompting, analogous to software design patterns.

If this is right

Prompts can be constructed by combining multiple patterns to handle complex tasks.
The catalog enables knowledge transfer of effective prompting strategies.
Patterns support automation of software development tasks using LLMs.
Outputs gain specific qualities and quantities as enforced by the patterns.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

Adopting these patterns could standardize prompt engineering practices across teams.
Future tools might automatically suggest or generate prompts based on the catalog.
The framework could extend to other AI systems beyond language models.
Testing the patterns on emerging LLMs would validate their broad applicability.

Load-bearing premise

The documented patterns will transfer effectively to new domains, tasks, and different large language models.

What would settle it

A controlled experiment showing that prompts built with the catalog produce no better results than ad-hoc prompts on a new set of tasks would falsify the claim.

read the original abstract

Prompt engineering is an increasingly important skill set needed to converse effectively with large language models (LLMs), such as ChatGPT. Prompts are instructions given to an LLM to enforce rules, automate processes, and ensure specific qualities (and quantities) of generated output. Prompts are also a form of programming that can customize the outputs and interactions with an LLM. This paper describes a catalog of prompt engineering techniques presented in pattern form that have been applied to solve common problems when conversing with LLMs. Prompt patterns are a knowledge transfer method analogous to software patterns since they provide reusable solutions to common problems faced in a particular context, i.e., output generation and interaction when working with LLMs. This paper provides the following contributions to research on prompt engineering that apply LLMs to automate software development tasks. First, it provides a framework for documenting patterns for structuring prompts to solve a range of problems so that they can be adapted to different domains. Second, it presents a catalog of patterns that have been applied successfully to improve the outputs of LLM conversations. Third, it explains how prompts can be built from multiple patterns and illustrates prompt patterns that benefit from combination with other prompt patterns.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

A practical catalog of prompt patterns for ChatGPT that organizes techniques like software design patterns, but rests success claims only on author examples without metrics or baselines.

read the letter

This paper's core offering is a catalog of reusable prompt patterns for LLMs, framed explicitly as an analog to software design patterns. The authors document a framework for describing these patterns so they transfer across domains and show how to combine them for tasks like code generation or requirements clarification. That structure is the main new piece here, and it gives practitioners a ready set of templates rather than scattered tips. The examples feel concrete and tied to software engineering workflows, which makes the work immediately usable for people already prompting LLMs in development settings. The documentation approach itself is a small but clear step forward for turning ad-hoc prompting into something more systematic. The main limitation is the evidence base. Claims that the patterns have been applied successfully come from the authors' own constructed demonstrations, with no A/B comparisons, user studies, accuracy measures, or baseline results reported. Readers are left to verify the improvements themselves. That keeps the contribution descriptive and practical rather than rigorously tested. The paper targets software engineers and prompt engineers who need quick, adaptable techniques for LLM-assisted automation. It will be most valuable to practitioners who want templates they can try immediately, and less so to researchers looking for quantified gains or formal analysis. I would bring it to a reading group to test a few patterns ourselves and discuss how the catalog could be extended. It deserves peer review because the organization fills a real gap in early prompt engineering work, even if referees will likely ask for more empirical grounding.

Referee Report

2 major / 2 minor

Summary. The manuscript presents a catalog of prompt patterns for enhancing interactions with LLMs like ChatGPT. It outlines a framework for documenting these patterns, provides examples of individual patterns and their combinations, and positions them as reusable solutions analogous to software design patterns for common problems in prompt engineering.

Significance. If the patterns prove effective, the work could provide a practical knowledge transfer mechanism for prompt engineering, helping developers and users structure prompts more systematically. The analogy to software patterns is apt and the framework for documentation is a useful contribution, though the absence of rigorous evaluation metrics means the significance is primarily in organization and illustration rather than proven efficacy.

major comments (2)

[Abstract] Abstract: The claim that the patterns 'have been applied successfully to improve the outputs of LLM conversations' is not backed by quantitative validation, error measures, or comparative baselines; the support consists solely of illustrative examples constructed by the authors.
[Contributions] Contributions: The second listed contribution asserts a catalog of successfully applied patterns, but the manuscript does not specify the criteria or evidence used to determine success, which directly affects the generalizability of the framework to different domains and LLMs.

minor comments (2)

[Introduction] Introduction: Consider adding more references to existing prompt engineering literature to better contextualize the novelty of the pattern catalog relative to prior work.
[Pattern catalog sections] Pattern descriptions: Some individual pattern sections could benefit from explicit discussion of potential limitations or edge cases where the pattern may not improve outputs.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive comments and recommendation for minor revision. We agree that the claims about successful application require clarification to accurately reflect the illustrative nature of the examples and the scope of the contribution as a framework and catalog.

read point-by-point responses

Referee: [Abstract] Abstract: The claim that the patterns 'have been applied successfully to improve the outputs of LLM conversations' is not backed by quantitative validation, error measures, or comparative baselines; the support consists solely of illustrative examples constructed by the authors.

Authors: We agree that the wording in the abstract could imply empirical validation beyond what is provided. The paper positions the patterns as reusable solutions analogous to software design patterns, where contributions typically begin with illustrative examples. In the revised manuscript, we will update the abstract to state that the patterns 'are illustrated through examples demonstrating their use in improving LLM conversation outputs,' thereby removing any implication of quantitative success and aligning the text with the paper's focus on organization and illustration. revision: yes
Referee: [Contributions] Contributions: The second listed contribution asserts a catalog of successfully applied patterns, but the manuscript does not specify the criteria or evidence used to determine success, which directly affects the generalizability of the framework to different domains and LLMs.

Authors: We accept this point and will revise the contributions section to explicitly state that the catalog is derived from the authors' practical experience applying the patterns to common prompt engineering tasks in software development contexts. Success is demonstrated qualitatively via the provided examples rather than formal criteria or metrics. We will also add text noting the framework's intended adaptability while acknowledging that broader empirical validation across domains and LLMs remains future work. revision: yes

Circularity Check

0 steps flagged

No significant circularity: descriptive catalog without derivations or self-referential reductions

full rationale

The paper is a descriptive catalog of prompt patterns for LLM interactions, providing a documentation framework and illustrative examples of patterns and their combinations. It contains no equations, fitted parameters, predictions, or derivation chains. Claims of successful application rest on author-constructed examples rather than quantitative metrics, but this is not circularity per the rules, as no step reduces by construction to its own inputs via self-definition, fitted inputs renamed as predictions, or load-bearing self-citations. The work is self-contained as a knowledge-transfer contribution analogous to software patterns, with no ansatzes smuggled via citation or uniqueness theorems imported from prior author work that would force the result.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The paper rests on the domain assumption that software engineering patterns translate directly to prompt engineering for LLMs, with no free parameters, invented entities, or additional axioms stated.

axioms (1)

domain assumption Prompt patterns provide reusable solutions to common problems in LLM output generation and interaction
Invoked in the abstract as the basis for the catalog and framework.

pith-pipeline@v0.9.0 · 5527 in / 984 out tokens · 47662 ms · 2026-05-15T07:04:31.897769+00:00 · methodology

discussion (0)

Forward citations

Cited by 20 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation
cs.CL 2026-05 unverdicted novelty 7.0

CA-SQL achieves 51.72% execution accuracy on the challenging tier of the BIRD benchmark using GPT-4o-mini by scaling exploration breadth according to estimated task difficulty, evolutionary prompt seeding, and candida...
When Prompt Under-Specification Improves Code Correctness: An Exploratory Study of Prompt Wording and Structure Effects on LLM-Based Code Generation
cs.SE 2026-04 unverdicted novelty 7.0

Structurally rich task descriptions make LLMs robust to prompt under-specification, and under-specification can enhance code correctness by disrupting misleading lexical or structural cues.
Figures as Interfaces: Toward LLM-Native Artifacts for Scientific Discovery
cs.HC 2026-04 unverdicted novelty 7.0

LLM-native figures embed provenance and enable direct LLM interaction with scientific visualizations to accelerate discovery and improve reproducibility.
Architecture Without Architects: How AI Coding Agents Shape Software Architecture
cs.SE 2026-04 unverdicted novelty 7.0

AI coding agents perform vibe architecting by making prompt-driven architectural choices that produce structurally different systems for identical tasks.
Automated Design of Agentic Systems
cs.AI 2024-08 conditional novelty 7.0

Meta Agent Search uses a meta-agent to iteratively program novel agentic systems in code, producing agents that outperform state-of-the-art hand-designed ones across coding, science, and math while transferring across...
Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
cs.CL 2026-05 unverdicted novelty 6.0

LLMs perform in-context learning as trajectories through a structured low-dimensional conceptual belief space, with the structure visible in both behavior and internal representations and causally manipulable via inte...
From Natural Language to Verified Code: Toward AI Assisted Problem-to-Code Generation with Dafny-Based Formal Verification
cs.SE 2026-04 unverdicted novelty 6.0

Open-weight LLMs reach 81-91% success generating formally verified Dafny code for complex algorithmic problems when given structural signatures and self-healing verifier feedback.
SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
cs.CR 2026-02 unverdicted novelty 6.0

The paper systematizes agentic skills beyond tool use, providing design pattern and representation-scope taxonomies plus security analysis of malicious skill infiltration in agent marketplaces.
Making OpenAPI Documentation Agent-Ready: Detecting Documentation and REST Smells with a Multi-Agent LLM System
cs.SE 2026-05 unverdicted novelty 5.0

Hermes uses multi-agent LLMs to detect 2450 documentation and REST smells across 600 OpenAPI endpoints, demonstrating that structurally valid microservice APIs are often not semantically ready for agent consumption.
The Readability Spectrum: Patterns, Issues, and Prompt Effects in LLM-Generated Code
cs.SE 2026-05 unverdicted novelty 5.0

LLM-generated code matches human-written code in overall readability but exhibits different issue patterns, and prompt engineering has limited impact on improving it.
User Reviews as a Source for Usability Requirements: A Precursor Study on Using Large Language Models
cs.SE 2026-05 conditional novelty 5.0

LLMs can detect usability content in user reviews with F-scores comparable to humans, though performance depends strongly on prompt design.
Benchmarking LLM-Based Static Analysis for Secure Smart Contract Development: Reliability, Limitations, and Potential Hybrid Solutions
cs.CR 2026-05 unverdicted novelty 5.0

LLMs for smart contract security analysis show lexical bias from identifier names causing high false positives, with prompting creating precision-recall trade-offs, positioning them as complements rather than replacem...
Conventional Commit Classification using Large Language Models and Prompt Engineering
cs.SE 2026-05 unverdicted novelty 5.0

Few-shot prompting with the 32B DeepSeek-R1 model achieves the highest accuracy on a balanced set of 3,200 conventional commits mined from InfluxDB, while chain-of-thought adds no benefit and larger model scale improv...
Enhanced Self-Learning with Epistemologically-Informed LLM Dialogue
cs.HC 2026-04 unverdicted novelty 5.0

CausaDisco integrates Aristotle's Four Causes into LLM prompts to produce more engaging, exploratory, and multifaceted self-learning dialogues, as evidenced by controlled user studies.
STaR-DRO: Stateful Tsallis Reweighting for Group-Robust Structured Prediction
cs.LG 2026-04 unverdicted novelty 5.0

STaR-DRO applies momentum-smoothed Tsallis reweighting to focus learning on hard groups in structured prediction, yielding F1 gains on clinical label extraction.
LLM2Manim: Pedagogy-Aware AI Generation of STEM Animations
cs.MM 2026-04 unverdicted novelty 5.0

LLM2Manim pipeline generates pedagogy-aware Manim animations for STEM, producing slightly better student post-test scores (83% vs 78%), learning gains (d=0.67), and engagement than PowerPoint in a controlled study.
The PICCO Framework for Large Language Model Prompting: A Taxonomy and Reference Architecture for Prompt Structure
cs.CL 2026-04 accept novelty 5.0

PICCO is a five-element reference architecture (Persona, Instructions, Context, Constraints, Output) for structuring LLM prompts, derived from synthesizing prior frameworks along with a taxonomy distinguishing prompt ...
Transparent and Controllable Recommendation Filtering via Multimodal Multi-Agent Collaboration
cs.IR 2026-04 unverdicted novelty 4.0

A multi-agent multimodal system with fact-grounded adjudication and a dynamic two-tier preference graph cuts false positives in content filtering by 74.3% and nearly doubles F1-score versus text-only baselines while s...
Nanomentoring: Investigating How Quickly People Can Help People Learn Feature-Rich Software
cs.HC 2026-04 unverdicted novelty 4.0

Experts can deliver helpful advice on over half of short 'nanoquestions' about feature-rich software in under one minute.
From System 1 to System 2: A Survey of Reasoning Large Language Models
cs.AI 2025-02 accept novelty 3.0

The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.

Reference graph

Works this paper leans on

38 extracted references · 38 canonical work pages · cited by 20 Pith papers · 5 internal anchors

[1]

On the Opportunities and Risks of Foundation Models

R. Bommasani, D. A. Hudson, E. Adeli, R. Altman, S. Arora, S. von Arx, M. S. Bernstein, J. Bohg, A. Bosselut, E. Brunskill et al. , “On the opportunities and risks of foundation models,” arXiv preprint arXiv:2108.07258, 2021

work page internal anchor Pith review Pith/arXiv arXiv 2021
[2]

A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and int eractivity,

Y . Bang, S. Cahyawijaya, N. Lee, W. Dai, D. Su, B. Wilie, H. Lovenia, Z. Ji, T. Y u, W. Chung et al. , “A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and int eractivity,” arXiv preprint arXiv:2302.04023 , 2023

work page arXiv 2023
[3]

How well does chatgpt do when taking the med ical licensing exams?

A. Gilson, C. Safranek, T. Huang, V . Socrates, L. Chi, R. A . Taylor, and D. Chartash, “How well does chatgpt do when taking the med ical licensing exams?” medRxiv, pp. 2022–12, 2022

work page 2022
[4]

Architecting the future of software engi neering,

A. Carleton, M. H. Klein, J. E. Robert, E. Harper, R. K. Cun ningham, D. de Niz, J. T. Foreman, J. B. Goodenough, J. D. Herbsleb, I. O zkaya, and D. C. Schmidt, “Architecting the future of software engi neering,” Computer, vol. 55, no. 9, pp. 89–93, 2022

work page 2022
[5]

Github copilot · your ai pair programmer

“Github copilot · your ai pair programmer.” [Online]. Av ailable: https://github.com/features/copilot

work page
[6]

Is github’s copilo t as bad as humans at introducing vulnerabilities in code?

O. Asare, M. Nagappan, and N. Asokan, “Is github’s copilo t as bad as humans at introducing vulnerabilities in code?” arXiv preprint arXiv:2204.04741, 2022

work page arXiv 2022
[7]

Asleep at the keyboard? assessing the security of github copilot’s co de contribu- tions,

H. Pearce, B. Ahmad, B. Tan, B. Dolan-Gavitt, and R. Karri , “Asleep at the keyboard? assessing the security of github copilot’s co de contribu- tions,” in 2022 IEEE Symposium on Security and Privacy (SP) . IEEE, 2022, pp. 754–768

work page 2022
[8]

Krochmalski, IntelliJ IDEA Essentials

J. Krochmalski, IntelliJ IDEA Essentials . Packt Publishing Ltd, 2014

work page 2014
[9]

Pre- train, prompt, and predict: A systematic survey of promptin g methods in natural language processing,

P . Liu, W. Y uan, J. Fu, Z. Jiang, H. Hayashi, and G. Neubig, “Pre- train, prompt, and predict: A systematic survey of promptin g methods in natural language processing,” ACM Computing Surveys, vol. 55, no. 9, pp. 1–35, 2023

work page 2023
[10]

Gamma, R

E. Gamma, R. Johnson, R. Helm, R. E. Johnson, and J. Vliss ides, Design patterns: elements of reusable object-oriented sof tware. Pearson Deutschland GmbH, 1995

work page 1995
[11]

D. C. Schmidt, M. Stal, H. Rohnert, and F. Buschmann, Pattern-oriented software architecture, patterns for concurrent and networ ked objects . John Wiley & Sons, 2013

work page 2013
[12]

ChatGPT: Large-Scale Generative Language Mo dels for Automated Content Creation,

OpenAI, “ChatGPT: Large-Scale Generative Language Mo dels for Automated Content Creation,” https://openai.com/blog/c hatgpt/, 2023, [Online; accessed 19-Feb-2023]

work page 2023
[13]

DALL·E 2: Creating Images from Text,

——, “DALL·E 2: Creating Images from Text,” https://openai.com/dall-e-2/ , 2023, [Online; accessed 1 9-Feb-2023]

work page 2023
[14]

Least-to-Most Prompting Enables Complex Reasoning in Large Language Models

D. Zhou, N. Sch¨ arli, L. Hou, J. Wei, N. Scales, X. Wang, D . Schu- urmans, O. Bousquet, Q. Le, and E. Chi, “Least-to-most promp ting enables complex reasoning in large language models,” arXiv preprint arXiv:2205.10625, 2022

work page internal anchor Pith review Pith/arXiv arXiv 2022
[15]

Graphviz and dynagraph—static and dynamic graph drawing t ools,

J. Ellson, E. R. Gansner, E. Koutsoﬁos, S. C. North, and G . Woodhull, “Graphviz and dynagraph—static and dynamic graph drawing t ools,” Graph drawing software , pp. 127–148, 2004

work page 2004
[16]

Building a virtual machine inside a javascrip t library,

S. Owen, “Building a virtual machine inside a javascrip t library,” https://www.engraved.blog/building-a-virtual-machine-inside/, 2022, accessed: 2023-02-20

work page 2022
[17]

Applying Software Patterns to Address Interoperability in Blockchain-based Healthcare Apps

P . Zhang, J. White, D. C. Schmidt, and G. Lenz, “Applying software patterns to address interoperability in blockcha in-based healthcare apps,” CoRR, vol. abs/1706.03700, 2017. [Online]. Available: http://arxiv.org/abs/1706.03700

work page internal anchor Pith review Pith/arXiv arXiv 2017
[18]

A pattern collection for blockchain-based applications,

X. Xu, C. Pautasso, L. Zhu, Q. Lu, and I. Weber, “A pattern collection for blockchain-based applications,” in Proceedings of the 23rd European Conference on Pattern Languages of Programs , 2018, pp. 1–20

work page 2018
[19]

Chatgpt: ﬁve priorities for research,

E. A. van Dis, J. Bollen, W. Zuidema, R. van Rooij, and C. L . Bockting, “Chatgpt: ﬁve priorities for research,” Nature, vol. 614, no. 7947, pp. 224–226, 2023

work page 2023
[20]

Prompt programming for la rge language models: Beyond the few-shot paradigm,

L. Reynolds and K. McDonell, “Prompt programming for la rge language models: Beyond the few-shot paradigm,” CoRR, vol. abs/2102.07350,

work page arXiv
[21]

Available: https://arxiv.org/abs/2102

[Online]. Available: https://arxiv.org/abs/2102. 07350

work page
[22]

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

J. Wei, X. Wang, D. Schuurmans, M. Bosma, E. H. Chi, Q. Le, and D. Zhou, “Chain of thought prompting elicits reasoning i n large language models,” CoRR, vol. abs/2201.11903, 2022. [Online]. Available: https://arxiv.org/abs/2201.11903

work page internal anchor Pith review Pith/arXiv arXiv 2022
[23]

Emergent Abilities of Large Language Models

J. Wei, Y . Tay, R. Bommasani, C. Raffel, B. Zoph, S. Borge aud, D. Y ogatama, M. Bosma, D. Zhou, D. Metzler, E. H. Chi, T. Hashimoto, O. Vinyals, P . Liang, J. Dean, and W. Fedus, “Em ergent abilities of large language models,” 2022. [Online]. Avail able: https://arxiv.org/abs/2206.07682

work page internal anchor Pith review Pith/arXiv arXiv 2022
[24]

Large language models are human-level prompt engine ers,

Y . Zhou, A. I. Muresanu, Z. Han, K. Paster, S. Pitis, H. Ch an, and J. Ba, “Large language models are human-level prompt engine ers,”

work page
[25]

Available: https://arxiv.org/abs/2211

[Online]. Available: https://arxiv.org/abs/2211. 01910

work page
[26]

Autoprompt: Eliciting knowledge from language models wit h automatically generated prompts,

T. Shin, Y . Razeghi, R. L. L. IV , E. Wallace, and S. Singh, “Autoprompt: Eliciting knowledge from language models wit h automatically generated prompts,” CoRR, vol. abs/2010.15980, 2020. [Online]. Available: https://arxiv.org/abs/2010.15980

work page arXiv 2010
[27]

Language models are unsupervised multitask learners,

A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, and I. Sut skever, “Language models are unsupervised multitask learners,” 20 19

work page
[28]

Least- to- most prompting enables complex reasoning in large language models,

D. Zhou, N. Sch¨ arli, L. Hou, J. Wei, N. Scales, X. Wang, D. Schuurmans, C. Cui, O. Bousquet, Q. Le, and E. Chi, “Least- to- most prompting enables complex reasoning in large language models,”

work page
[29]

Available: https://arxiv.org/abs/2205

[Online]. Available: https://arxiv.org/abs/2205. 10625

work page
[30]

Maieutic prompting: Logically consiste nt reasoning with recursive explanations,

J. Jung, L. Qin, S. Welleck, F. Brahman, C. Bhagavatula, R. L. Bras, and Y . Choi, “Maieutic prompting: Logically consiste nt reasoning with recursive explanations,” 2022. [Online]. A vailable: https://arxiv.org/abs/2205.11822

work page arXiv 2022
[31]

Ask me anything: A simple strategy for prompting language models,

S. Arora, A. Narayan, M. F. Chen, L. Orr, N. Guha, K. Bhatia, I. Chami, and C. Re, “Ask me anything: A simple strategy for prompting language models,” in International Conference on Learning Representations , 2023. [Online]. Available: https://openreview.net/forum?id=bhUPJnS2g0X

work page 2023
[32]

Design guidelines for prompt e ngineering text-to-image generative models,

V . Liu and L. B. Chilton, “Design guidelines for prompt e ngineering text-to-image generative models,” in Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems , 2022, pp. 1–23

work page 2022
[33]

Chat2vis: Generating data visualisations via natural language using chatgpt, codex and gpt-3 large la nguage models,

P . Maddigan and T. Susnjak, “Chat2vis: Generating data visualisations via natural language using chatgpt, codex and gpt-3 large la nguage models,” arXiv preprint arXiv:2302.02094 , 2023

work page arXiv 2023
[34]

Ptr: Prompt t uning with rules for text classiﬁcation,

X. Han, W. Zhao, N. Ding, Z. Liu, and M. Sun, “Ptr: Prompt t uning with rules for text classiﬁcation,” AI Open , vol. 3, pp. 182–192, 2022

work page 2022
[35]

Can chatg pt write a good boolean query for systematic review literature searc h?

S. Wang, H. Scells, B. Koopman, and G. Zuccon, “Can chatg pt write a good boolean query for systematic review literature searc h?” arXiv preprint arXiv:2302.03495 , 2023

work page arXiv 2023
[36]

Conversational automated progr am repair,

C. S. Xia and L. Zhang, “Conversational automated progr am repair,” arXiv preprint arXiv:2301.13246 , 2023

work page arXiv 2023
[37]

C hatgpt goes to law school,

J. H. Choi, K. E. Hickman, A. Monahan, and D. Schwarcz, “C hatgpt goes to law school,” Available at SSRN , 2023

work page 2023
[38]

Mathematical c apabilities of chatgpt,

S. Frieder, L. Pinchetti, R.-R. Grifﬁths, T. Salvatori , T. Lukasiewicz, P . C. Petersen, A. Chevalier, and J. Berner, “Mathematical c apabilities of chatgpt,” arXiv preprint arXiv:2301.13867 , 2023

work page arXiv 2023