The paper addresses the problem of making legal decisions about regulations such that they are compliant with legal principles. While decision-making using legal rules is well-developed in the literature, few researchers address reasoning with principles. A key difference between applying rules versus principles is that rules have a binary character, they are applied or not, while principles can be applied to a certain extent and in the case of conflicting principles, they require balancing instead of defeat. This paper provides a novel approach to balancing principles and deciding amongst regulations by proportional optimisation of values associated with regulations and principles. The approach can be generalised to other areas of decision-making.

Research in AI and Law has traditionally focused on case-based reasoning in common law systems, where factual similarity and factor-based modeling dominate. Much less attention has been given to continental jurisdictions, where judicial decisions are formally non-binding but still exert significant interpretive influence. This paper investigates how precedents function as interpretive resources in statutory reasoning, using the Polish Supreme Court decision as a case study. We use the case frame method, which structures judicial reasoning into slots: interpreted provision, competing interpretations, supporting arguments, meta-rules, and final decision. By applying this model to the source case and its reception in later case law, we identify three recurring patterns: (i) cross-domain influence, where the interpretive meta-rule travels across criminal, administrative, and transitional justice contexts; (ii) different takeaways, where distinct interpretive holdings (e.g., evidentiary standards, procedural guarantees) are extracted from the same judgment; and (iii) modificatory application, where courts cite the precedent but reshape its operative force.

We introduce a novel conceptual Case Frame model that represents the content of cases involving statutory interpretation within civil law frameworks, accompanied by an associated argument scheme enriched with critical questions. By validating our approach with a modest dataset, we demonstrate its robustness and practical applicability. Our model not only provides a structured method for analyzing statutory interpretation but also highlights the distinct needs of lawyers operating under statutory law compared to those reasoning with common law precedents. The model presented here is a step towards developing a hybrid Machine LearningArgumentation system that includes a module for constructing well-structured arguments from textual datasets

We present an approach designed to support the process of legislative drafting by helping to detect errors in a normative text. It is based on a framework allowing for representation and comparison of structure and semantic content of legal provisions. Such comparison serves as a starting point for detection of (potential) legislative errors. The approach provides in particular criteria to select provisions to be compared, related to the phenomenon of provisions overlapping. We show that specific cases of such an overlap may amount to legislative errors. The presented framework enables a precise and transparent account of these errors. We also acknowledge that textual provisions enable various interpretations, while the error methodology detection assumes that the semantic representation of provisions is a result of a specific interpretation. We introduce the notion of Constraining Interpretive Rules which are used to evaluate the acceptability of specific interpretations of legal provisions. We discuss the features of the model on a real example and we present an implementation of the approach by using semantic technologies.

This paper introduces a framework of conceptual structures allocated to statutory expressions during interpretive heuresis. Drawing from cognitive science research on conceptual structures, the study seeks to enhance existing computational models of legal reasoning across various domains. A comprehensive set of conceptual structures applicable in statutory interpretation is reconstructed. This framework increases awareness of potential interpretive options and contributes to the transparency of legal reasoning.

This paper extends the existing account of statutory interpretation based on argument schemes theory. It points out that the preference relations among statutory canons are not always determined by some predefined rules, but in certain systems of law or legal domains, it is necessary to argue these preference relations on the basis of case law. A set of factors favouring linguistic arguments and teleological arguments is presented, and a case-based argument scheme for the assignment of preference relations is reconstructed.

In this paper, we examine the use of multi-lingual sentence embeddings to transfer predictive models for functional segmentation of adjudicatory decisions across jurisdictions, legal systems (common and civil law), languages, and domains (i.e. contexts). Mechanisms for utilizing linguistic resources outside of their original context have significant potential benefits in AI & Law because differences between legal systems, languages, or traditions often block wider adoption of research outcomes. We analyze the use of Language-Agnostic Sentence Representations in sequence labeling models using Gated Recurrent Units (GRUs) that are transferable across languages. To investigate transfer between different contexts we developed an annotation scheme for functional segmentation of adjudicatory decisions. We found that models generalize beyond the contexts on which they were trained (e.g., a model trained on administrative decisions from the US can be applied to criminal law decisions from Italy). Further, we found that training the models on multiple contexts increases robustness and improves overall performance when evaluating on previously unseen contexts. Finally, we found that pooling the training data from all the contexts enhances the models' in-context performance.

This paper presents a Semantic Web–based model for detecting contradictions in regulations. We introduce a conceptual model of contradictions and, on the basis of this model, a knowledge representation–based model is used, which is able to represent the semantics of provision types and related properties. The usefulness of the model is shown through an example.

The paper discusses the problem of formal modeling of the interpretation of statutory legal norms.The authors propose a comprehensive framework that allows the representation of the interpretation process.The authors' proposal is illustrated by a real-life example.

The paper presents a general formal framework representing the role of balancing of values in interpretation of statutory rules. The model developed here is an extension of the model of teleological interpretation, where a given interpretive outcome is justified if it satisfies a given goal (or a set of goals). Herein, a richer argumentative structure is discussed: an interpretive proposition concerning the interpretation of a statutory condition is justified if it is in accordance with the proper balance of applicable legally relevant values.

This paper presents a theoretical account of legal validity. We begin with a very simple criterial account of validity and discuss the possibility of elimination of such concept by means of procedure described in Ross' paper Tû-Tû. Then we discuss more ambitious theoretical proposals concerning validity, advocated by Grabowski and Sartor. We make an attempt to reconcile and further generalize these accounts. Finally, we focus on the broadest view encompassing the role of institutions with regard to validity. The notion of intermediate anchoring institutions is key in the new social scenarios created through linked-data systems. Some examples are provided.

This paper contributes to the formal research on legal interpretation by presenting a structure of normative agents. Each normative agent consists of a knowledge base, a set of preferences, and certain procedures related to the interpretation conducted by this agent. A part of typology of normative agents is presented. The investigations are illustrated with a model of a real-life example.

This paper shows how a complex legal doctrinal theory (the doctrine of causation in law) may be represented in a semi-formal, two-layered model of statutory interpretation. The content of the theory is clarified by the proposed knowledge representation. It is argued that doctrinal theories in the reading proposed here are a source of intermediate legal concepts and, in consequence, of rules that enable the judge to argue efficiently in complex cases without entering into wider considerations involving case-based reasoning structures.

This paper evaluates the Parenting Plan Support System, a partially implemented decision support system designed to help parents to draft an agreement concerning relations with their children after the divorce, against the background of a real-life case. The focus here is on knowledge representation issues and the functioning of the inference engine.

The paper discusses the complexity problem in the interpretation of statutory legal norms. The authors propose a comprehensive framework that allows the representation of the interpretation process.

A factor-based approach to case-based reasoning has been successfully applied in the field of AI and Law to model legal arguments in adversarial judicial procedures. In this paper, we discuss how factors and dimensions can be applied in a dispute-support system that aims to reconcile inconsistent interests of the parties for the sake of a higher-order value, that is, the well being of a child.

The paper presents a model of teleological interpretation of statutory legal rules as well as an example of the genuine law case, which has been modeled with use of established methodology.

This paper proposes a semi-formal model of legal argumentation concerning statutory interpretation in civil law countries, encompassing set-theoretical analysis of extensions of legal terms and the use of argumentation schemes. An actual example decided by the Polish Supreme Administrative Court is discussed in the context of the proposed model. It is contended that the scheme proposed here should be useful for the development of practically significant legal knowledge bases concerning statutory law.

In this paper we present a refined coherence as constraint satisfaction framework as a potent tool for representation of judicial reasoning. We demonstrate usefulness of the framework on a model of the famous Popov v Hayashi case. Although we do not claim that the presented framework can be already considered fully developed we believe that the account constitutes a major improvement over those that have been published previously. The resulting representation is strongly anchored in a raw text of the decision itself and by means of formal logic can be transformed to a graphical representation which is a surprisingly intuitive and transparent account of application of rules in legal cases.

Analogy has been considered in AI and law primarily in relation to reasoning from precedent cases rather than reasoning from statutes. Where a statutory provision does not apply to a case, the principle of e contrario, that if the case is not covered by the rule the negation of the conclusion can be taken as established, has typically been assumed to apply. There are, however, cases where analogy is an appropriate way to bring a case under a statutory rule. In this paper we discuss using analogy in reasoning with states, and where this should be avoided and e contrario followed. Our account will be based on the notion of factors as developed in AI and law case based reasoning.

Robert Alexy is one of the main advocates of the so-called Rules and Principles Theory (hereafter: RPT). According to the RPT, legal norms can be divided into legal rules and legal principles. One of the main criteria for this distinction is - Alexy argues - that legal rules are applied by means of the Subsumption Formula, while legal principles - by means of the so-called Weight Formula (hereafter: WF). The WF offers an important insight into the structure of the process of balancing in legal reasoning. Alexy's proposal leads to many doubts and questions, however. The aim of the paper is to examine the appropriateness of the WF and the problem of balancing in legal reasoning from the perspective inspired by the constraint satisfaction theory of coherence, developed by Paul Thagard. My claim is that this theory enables us to elucidate many problematic features of the WF and to recast the structure of legal balancing in more transparent and efficient manner. The existing workable algorithms designed for computing other kinds of coherence-based reasoning (for instance, explanatory reasoning or analogical reasoning), make possible to adopt the programs employing these algorithms for computation of coherence in balancing of principles. However, the analysis presented here is mainly conceptual and it has only preparatory character in relation with the possible computational implementations in the future.