REVIEW 7 cited by
ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
This paper presents prompt design techniques for software engineering, in the form of patterns, to solve common problems when using large language models (LLMs), such as ChatGPT to automate common software engineering activities, such as ensuring code is decoupled from third-party libraries and simulating a web application API before it is implemented. This paper provides two contributions to research on using LLMs for software engineering. First, it provides a catalog of patterns for software engineering that classifies patterns according to the types of problems they solve. Second, it explores several prompt patterns that have been applied to improve requirements elicitation, rapid prototyping, code quality, refactoring, and system design.
Forward citations
Cited by 7 Pith papers
-
QUARE: Quality-Aware Requirements Analysis through Multi-Agent Dialectical Negotiation
Quality-specialized LLM agents that dialectically negotiate cross-quality conflicts produce more balanced, standards-compliant KAOS requirements than task- or knowledge-decomposed multi-agent RE baselines.
-
Knowledge-Enhanced Program Repair for Data Science Code
DSrepair combines a knowledge graph of data science APIs with AST-level bug localization to repair LLM-generated code, fixing more DS-1000 tasks than five baseline repair methods.
-
Development of Automated Software Design Document Review Methods Using Large Language Models
Converting tabular design documents into header-aware Markdown or JSON formats lets GPT models catch cross-document inconsistencies with recall up to 0.96 on short documents, but performance collapses beyond 5000 characters.
-
SnipGen: A Mining Repository Framework for Evaluating LLMs for Code
A new framework mines recent GitHub commits into about 227K method-level code snippets with prompt templates for testing LLMs on code generation while reducing training-data contamination.
-
Using ChatGPT to refine draft conceptual schemata in supply-driven design of multidimensional cubes
Prompt-engineered ChatGPT can partially automate refinement of draft multidimensional schemata, reducing errors from 9 to 4 per case, but human designer oversight remains necessary.
-
Supporting architecture evaluation for ATAM scenarios with LLMs
An initial study suggests an LLM with retrieval-augmented generation can add risks, sensitivity points, and tradeoffs to student-led ATAM architecture evaluations, though accuracy was not independently measured.
-
Toward Neurosymbolic Program Comprehension
The paper outlines the Neurosymbolic Program Comprehension (NsPC) framework and provides preliminary evidence that SHAP-value patterns over AST-tagged token positions can be interpreted as symbolic rules for insecure ...
Discussion (0). Continue with ORCID to comment.