Normative Requirements Operationalization with Large Language Models

被引:2
|
作者
Feng, Nick [1 ]
Marsso, Lina [1 ]
Yaman, Sinem Getir [2 ]
Standen, Isobel [2 ]
Baatartogtokh, Yesugen [1 ]
Ayad, Reem [1 ]
de Mello, Victoria Oldemburgo [1 ]
Townsend, Beverley [2 ]
Bartels, Hanne [1 ]
Cavalcanti, Ana [2 ]
Calinescu, Radu [2 ]
Chechik, Marsha [1 ]
机构
[1] Univ Toronto, Toronto, ON, Canada
[2] Univ York, York, England
关键词
D O I
10.1109/RE59067.2024.00022
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Normative non-functional requirements specify constraints that a system must observe in order to avoid violations of social, legal, ethical, empathetic, and cultural norms. As these requirements are typically defined by non-technical system stakeholders with different expertise and priorities (ethicists, lawyers, social scientists, etc.), ensuring their well-formedness and consistency is very challenging. Recent research has tackled this challenge using a domain-specific language to specify normative requirements as rules whose consistency can then be analysed with formal methods. In this paper, we propose a complementary approach that uses Large Language Models to extract semantic relationships between abstract representations of system capabilities. These relations, which are often assumed implicitly by non-technical stakeholders (e.g., based on common sense or domain knowledge), are then used to enrich the automated reasoning techniques for eliciting and analyzing the consistency of normative requirements. We show the effectiveness of our approach to normative requirements elicitation and operationalization through a range of real-world case studies.
引用
收藏
页码:129 / 141
页数:13
相关论文
共 50 条
  • [31] Large Language Models in der WissenschaftLarge language models in science
    Karl-Friedrich Kowalewski
    Severin Rodler
    Die Urologie, 2024, 63 (9) : 860 - 866
  • [32] Operationalization of Earth Observation - Its prospects and requirements
    MacDonald, JD
    OBSERVING LAND FROM SPACE: SCIENCE, CUSTOMERS AND TECHNOLOGY, 2000, 4 : 35 - 46
  • [33] The Importance of Understanding Language in Large Language Models
    Youssef, Alaa
    Stein, Samantha
    Clapp, Justin
    Magnus, David
    AMERICAN JOURNAL OF BIOETHICS, 2023, 23 (10): : 6 - 7
  • [34] Dissociating language and thought in large language models
    Mahowald, Kyle
    Ivanova, Anna A.
    Blank, Idan A.
    Kanwisher, Nancy
    Tenenbaum, Joshua B.
    Fedorenko, Evelina
    TRENDS IN COGNITIVE SCIENCES, 2024, 28 (06) : 517 - 540
  • [35] On the creativity of large language models
    Franceschelli, Giorgio
    Musolesi, Mirco
    AI & SOCIETY, 2024,
  • [36] Large language models and psychiatry
    Orru, Graziella
    Melis, Giulia
    Sartori, Giuseppe
    INTERNATIONAL JOURNAL OF LAW AND PSYCHIATRY, 2025, 101
  • [37] Large Language Models in Cyberattacks
    S. V. Lebed
    D. E. Namiot
    E. V. Zubareva
    P. V. Khenkin
    A. A. Vorobeva
    D. A. Svichkar
    Doklady Mathematics, 2024, 110 (Suppl 2) : S510 - S520
  • [38] Autoformalization with Large Language Models
    Wu, Yuhuai
    Jiang, Albert Q.
    Li, Wenda
    Rabe, Markus N.
    Staats, Charles
    Jamnik, Mateja
    Szegedy, Christian
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35, NEURIPS 2022, 2022,
  • [39] Imitation and Large Language Models
    Boisseau, Eloise
    MINDS AND MACHINES, 2024, 34 (04)
  • [40] The Smallness of Large Language Models
    Denning, Peter J.
    COMMUNICATIONS OF THE ACM, 2023, 66 (09) : 24 - 27