Background/Context: Large Language Models (LLMs) demonstrate strong performance on low-dimensional software engineering optimization tasks ($\le$11 features) but consistently underperform on high-dimensional problems where Bayesian methods dominate. A fundamental gap exists in understanding how systematic integration of domain knowledge (whether from humans or automated reasoning) can bridge this divide.
Objective/Aim: We compare human versus artificial intelligence strategies for generating domain knowledge. We systematically evaluate four distinct architectures to determine if structured knowledge integration enables LLMs to generate effective warm starts for high-dimensional optimization.
Method: We evaluate four approaches on MOOT datasets stratified by dimensionality: (1) Human-in-the-Loop Domain Knowledge Prompting (H-DKP), utilizing asynchronous expert feedback loops; (2) Adaptive Multi-Stage Prompting (AMP), implementing sequential constraint identification and validation; (3) Dimension-Aware Progressive Refinement (DAPR), conducting optimization in progressively expanding feature subspaces; and (4) Hybrid Knowledge-Model Approach (HKMA), synthesizing statistical scouting (TPE) with RAG-enhanced prompting. Performance is quantified via Chebyshev distance to optimal solutions and ranked using Scott-Knott clustering against an established baseline for LLM generated warm starts.
Note that all human studies conducted as part of this study will comply with the policies of our local Institutional Review Board.
From Prompting to Engineering: A Research Agenda for Prompt Engineering in Software Engineering
Universitat Politècnica de Catalunya(加泰罗尼亚理工大学);CNR(意大利国家研究委员会);Pegaso University(佩加索大学);University of Gothenburg and Chalmers University of Technology(哥德堡大学与查尔姆斯理工大学);Politecnico di Torino(都灵理工大学);University of Glasgow(格拉斯哥大学);Tampere University(坦佩雷大学)
TraceLLM: Leveraging Large Language Models with Prompt Engineering for Enhanced Requirements Traceability
KFUPM(国王法赫德石油矿物大学);Imam Abdulrahman Bin Faisal University(伊玛目阿卜杜勒拉赫曼·本·费萨尔大学);SDAIA–KFUPM Joint Research Center of Artificial Intelligence, KFUPM(沙特数据与人工智能中心-国王法赫德石油矿物大学人工智能联合研究中心);University of Quebec in Montreal(蒙特利尔魁北克大学)
When Prompt Engineering Meets Software Engineering: CNL-P as Natural and Robust "APIs'' for Human-AI Interaction
CSIRO’s Data61(CSIRO数据61实验室);Jiangxi Provincial Key Laboratory for High Performance Computing(江西省高性能计算重点实验室);State International Science & Technology Cooperation Base of Networked Supporting Software(网络化支持软件国际科技合作基地);Language Intelligence Research Center(语言智能研究中心);Jiangxi Normal University(江西师范大学);Institute of AI, Newcastle University, UK(人工智能研究院,新castle大学,英国);UGAiForge
Prompt Engineering Strategies for LLM-based Qualitative Coding of Psychological Safety in Software Engineering Communities: A Controlled Empirical Study
Federal University of Bahia(巴伊亚联邦大学);State University of Feira de Santana(费拉德桑塔纳州立大学);Federal University of Sergipe(塞格皮联邦大学);Federal Institute of Ceara(塞阿拉联邦理工学院)
Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study
Nanyang Technological University(南洋理工大学);University of New South Wales(新南威尔士大学);Virginia Tech(弗吉尼亚理工大学);Huazhong University of Science and Technology(华中科技大学)