paper-with-me

홈 › Papers

Automated legal reasoning with discretion to act using s(LAW)

2024-01-25 · Joaquín Arias, Mar Moreno-Rebato, José A. Rodríguez-García, Sascha Ossowski

Automated legal reasoning and its application in smart contracts and automated decisions are increasingly attracting interest. In this context, ethical and legal concerns make it necessary for automated reasoners to justify in human-understandable terms the advice given. Logic Programming, specially Answer Set Programming, has a rich semantics and has been used to very concisely express complex knowledge. However, modelling discretionality to act and other vague concepts such as ambiguity cannot be expressed in top-down execution models based on Prolog, and in bottom-up execution models based on ASP the justifications are incomplete and/or not scalable. We propose to use s(CASP), a top-down execution model for predicate ASP, to model vague concepts following a set of patterns. We have implemented a framework, called s(LAW), to model, reason, and justify the applicable legislation and validate it by translating (and benchmarking) a representative use case, the criteria for the admission of students in the "Comunidad de Madrid".

📄 PDF Abstract BibTeX arXiv:2401.14511

Code (0)

등록된 구현이 없습니다.

Tasks

BenchmarkingLegal Reasoning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

When Fairness Isn't Statistical: The Limits of Machine Learning in Evaluating Legal Reasoning

2025-06-04 · Claire Barale, Michael Rovatsos, Nehal Bhuta

Legal decisions are increasingly evaluated for fairness, consistency, and bias using machine learning (ML) techniques. In high-stakes domains like refugee adjudication, such methods are often applied to detect disparitie…

ClusteringFairnessLegal Reasoning

AI Alignment at Your Discretion

2025-02-10 · Maarten Buyl, Hadi Khalaf, Claudio Mayrink Verdun, Lucas Monteiro Paes 외

In AI alignment, extensive latitude must be granted to annotators, either human or algorithmic, to judge which model outputs are `better' or `safer.' We refer to this latitude as alignment discretion. Such discretion rem…

Safety Alignment

Legal Rule Induction: Towards Generalizable Principle Discovery from Analogous Judicial Precedents

2025-05-20 · Wei Fan, Tianshi Zheng, Yiran Hu, Zheye Deng 외

Legal rules encompass not only codified statutes but also implicit adjudicatory principles derived from precedents that contain discretionary norms, social morality, and policy. While computational legal research has adv…

Hallucination

Challenges for Generative AI in Legal Reasoning

2025-08-26 · Eljas Linna, Tuula Linna arxiv

Large Language Models (LLMs) are being integrated into professional domains, yet their limitations in such high-stakes fields as law remain poorly understood. In response, this paper introduces examples of critical chall…

Legal Reasoning

Modelling Value-oriented Legal Reasoning in LogiKEy

2020-06-23 · Christoph Benzmüller, David Fuenmayor, Bertram Lomfeld

The logico-pluralist LogiKEy knowledge engineering methodology and framework is applied to the modelling of a theory of legal balancing in which legal knowledge (cases and laws) is encoded by utilising context-dependent …

Automated Theorem ProvingLegal Reasoning