We introduce JBE-QA, a Japanese Bar Exam Question-Answering dataset to evaluate large language models' legal knowledge. Derived from the multiple-choice (tanto-shiki) section of the Japanese bar exam (2015-2024), JBE-QA provides the first comprehensive benchmark for Japanese legal-domain evaluation of LLMs. It covers the Civil Code, the Penal Code, and the Constitution, extending beyond the Civil Code focus of prior Japanese resources. Each question is decomposed into independent true/false judgments with structured contextual fields. The dataset contains 3,464 items with balanced labels. We evaluate 26 LLMs, including proprietary, open-weight, Japanese-specialised, and reasoning models. Our results show that proprietary models with reasoning enabled perform best, and the Constitution questions are generally easier than the Civil Code or the Penal Code questions.

• Two-step approach (Named Entity Recognition + Rules) performed better than a direct code generation approach for natural language to PROLEG translation. • Regarding Large Language Models (LLMs), code LLMs (designed for code generation) did not show better results than general-purpose LLMs. • Llama 3 70B obtained better results for direct code generation than other models, including Llama 3.1 70B. • A NER library (GliNER) showed better performance than state-of-the-art Large Language Models, among which Llama 3.1 70B achieves the best results. This study presents a comparative analysis of methodologies for automating the extraction of legal information from contract texts and expressing it as PROLEG logical clauses, focusing on two approaches: Direct Code Generation (DCG) via Large Language Model (LLM) prompting, and Named Entity Recognition (NER) with rule-based transformation. For the NER-based approach, we evaluated three implementations: (1) LLM prompting for entity recognition, (2) a fine-tuned LLM for NER, and (3) a specialized NER library. Our findings reveal that while LLMs demonstrate versatility in general NLP tasks, the highest precision and contextual adaptation were achieved using a NER library specifically tailored to handle named entities. For finding named entities relevant to the contract (including, for instance, the buyer or the rescission date of a contract), this approach outperformed both DCG and NER using LLMs. The results underscore the importance of tailored lexical resources and rule-based post-processing in legal NLP applications, suggesting a paradigm for optimizing automated contract analysis systems, as opposed to the current trend of using general-purpose LLMs for most NLP tasks.

In this paper, we propose a pipeline leveraging Large Language Models (LLMs) for data augmentation in Information Extraction tasks within the legal domain. The proposed method is both simple and effective, significantly reducing the manual effort required for data annotation while enhancing the robustness of Information Extraction systems. Furthermore, the method is generalizable, making it applicable to various Natural Language Processing (NLP) tasks beyond the legal domain.

Case-based reasoning (CBR) is central to legal practice, relying on precedents to interpret and apply the law. Various formalisms have been proposed to represent cases, including cases represented as situation-outcome pairs (situation-outcome cases) and cases represented as logical formulas (logical cases). Connections between situation-outcome cases and logical cases have been preliminary explored, but interoperability between CBR models of these representations remains underexamined. To address this gap, this paper introduces four formal tools: (1) compatibility, which concerns interpolating a logical case into multiple situation-outcome cases; (2) enumerators, which generalise compatibility by interpolating logical case models into valid situation-outcome cases; (3) prototypers, which relate logical case models to reflexive and consistent situation-outcome CBR models, as illustrated by AA-CBR and the result model of precedential constraint; and (4) translators, which attempting the reverse, namely connecting such situation-outcome CBR models back to logical case models. Our investigation of these tools reveal how implicit cases can be introduced to simulate or align with another CBR model’s reasoning, which contributes to interoperability between CBR models.

We summarize the 12th Competition on Legal Information Extraction and Entailment. In this edition, the competition included four tasks on case law and statute law, plus a new pilot task on Tort law. The case law component includes an information retrieval task (Task 1), and the confirmation of an entailment relation between an existing case and an unseen case (Task 2). The statute law component includes an information retrieval task (Task 3), and an entailment/question-answering task based on retrieved civil code statutes (Task 4). The new pilot task is tort prediction (TP) and its rationale extraction (RE).

In the legal field, accurately interpreting and applying legal definitions is crucial yet challenging due to inherent ambiguities. This paper introduces DeCoRA, a novel framework that enhances legal argumentation by incorporating context-based reasoning to address these ambiguities, with a focus on the judge as the central decision maker. Unlike black-box models, such as generative models or outcome prediction systems, which often produce outputs without fully explaining the reasoning behind their conclusions, DeCoRA emphasizes transparency by modeling the judicial decision-making process in a structured and interpretable manner. Our key contributions include: (1) a tree-based knowledge base that organizes legal definitions, highlighting their relationships and effects; (2) a context-aware definition framework enabling judges to interpret definitions considering legal and contextual relevance; and (3) an effective method for handling complex legal scenarios with conflicting or overlapping definitions.

Ensuring autonomous vehicles (AVs) adhere to traffic rules is crucial for safety. Formalizing these rules into machine-readable formats offers a consistent, unambiguous foundation for automated reasoning and compliance. However, the formalization process is traditionally manual, resource-intensive, and prone to error. This study explores using large language models (LLMs) to automate the translation of traffic rules into PROLOG, a declarative programming language ideal for encoding logical rules and relationships. The proposed methodology consists of three key phases: extracting traffic rules from diverse textual sources, structuring them into Logical English (LE) for clarity and consistency, and translating them into PROLOG representations using advanced natural language processing (NLP) techniques, including in-context learning and fine-tuning. The experimental results demonstrate the effectiveness of LLMs in automating this process, achieving high accuracy in translation. The findings underscore the potential for scaling this methodology to accommodate broader regulatory frameworks, paving the way for safer, more reliable AV operations in complex and dynamic traffic environments.

Precedential constraint is one foundation of case-based reasoning in AI and Law. It generally assumes that the underlying set of precedents must be consistent. To relax this assumption, a generalized notion of the reason model has been introduced. While several argumentative explanation approaches exist for reasoning with precedents based on the traditional consistent reason model, there has been no corresponding argumentative explanation method developed for this generalized reasoning framework accommodating inconsistent precedents. To address this question, this paper examines an extension of the derivation state argumentation framework (DSA-framework) to explain the reasoning according to the generalized notion of the reason model.

Court decision summarization is challenging due to the significant length and structural complexity of legal documents, which makes existing reinforcement learning (RL)-based abstractive summarization methods less effective. We propose an RL-based abstractive legal summarization model with a novel argument-structured reward mechanism. It leverages Issue–Reason–Conclusion components to compute fine-grained sub-rewards and aggregate them into a final reward. This design provides more reliable learning signals for model optimization. Experiments on the Indian Supreme Court dataset with Longformer-Encoder-Decoder (LED) and Llama demonstrate consistent improvements over non-argument-structured methods. To the best of our knowledge, this is the first work to incorporate argumentative structures into RL-based summarization, offering a novel direction for improving legal summarization.

Guiding principles (Leits´latze) are central to German jurisprudence, capturing the essence of judicial reasoning in concise, doctrinally precise statements. Unlike general case summaries, they distill normative reasoning and key legal holdings rather than recounting factual backgrounds or procedural details. This paper examines how large language models (LLMs) can automatically generate guiding principles from German court decisions, focusing on three dimensions: model choice and adaptation, prompting strategies, and evaluation methods. Comparing GPT-4o with LerLeoLM, a fine-tuned, domain-specific model, we find that GPT-4o outperforms even without fine-tuning, while lightweight tuning on only 100 cases yields the best results. Human–LLM co-designed prompts further enhance quality, surpassing both expert-structured and self-generated prompts. Finally, we show that LLM-based evaluation aligns more closely with expert judgment than traditional metrics, establishing guiding principle generation as a distinct task in Legal NLP.

This paper presents an outline of our research project developed at our research center for "Juris-Informatics". "Juris-Informatics" is a research field based on two main topics; "Law by AI" and "Law of AI". "Law by Ai" is a research field where we investigate a support tool by AI for legal activities such as legal reasoning and legal document processing. "Law of AI" is a research field where we conduct research on legal control of AI such as considering the legal responsibility of AI and legal compliance of AI.

Retrieval-Augmented Generation (RAG) systems have shown potential in improving legal question-answering applications. However, they often struggle to provide precise information for legal queries, as broad-topic relevance may not always align with contextual usefulness. To address this challenge, we introduce Constrained Retrieval-Augmented Generation (ConsRAG), a novel approach that employs aspect-based constraints during both retrieval and generation phases. ConsRAG aims to enhance precision and contextual relevance in legal outputs through these constraints and an iterative backtracking mechanism. Our experiments suggest that ConsRAG may offer improvements over existing systems in terms of accuracy and relevance of retrieved documents. This paper presents the framework, implementation, and evaluation of ConsRAG, exploring its potential to enhance the reliability of legal AI applications.

The development of autonomous vehicles (AVs) requires a comprehensive understanding of both explicit and implicit traffic rules to ensure legal compliance and safety. While explicit traffic laws are well-defined in statutes and regulations, implicit rules derived from judicial interpretations and case law are more nuanced and challenging to extract. This research investigates the potential of Large Language Models (LLMs), particularly GPT-4o, in automating the extraction of implicit traffic rules from judicial decisions. By utilizing various prompt engineering techniques, including Standard Prompts, Chain-of-Thought (CoT), Chain-of-Instructions (CoI), and Layer-of-Thought (LoT) prompts, this study aims to assess the effectiveness of GPT-4o in identifying normative content relevant to specific traffic laws. The contributions of this paper include an assessment of LLMs for legal text processing, the automation of implicit rule extraction, and the development of a scalable framework that can continuously update as new legal precedents emerge. The results indicate promising avenues for integrating automated normative extraction in AV systems, improving both the safety and legal compliance of autonomous driving technologies.

We summarize the 10th Competition on Legal Information Extraction and Entailment. In this edition, the competition included four tasks on case law and statute law. The case law component includes an information retrieval task (Task 1), and the confirmation of an entailment relation between an existing case and an unseen case (Task 2). The statute law component includes an information retrieval task (Task 3), and an entailment/question answering task based on retrieved civil code statutes (Task 4). Participation was open to any group based on any approach. Ten different teams participated in the case law competition tasks, most of them in more than one task. We received results from 8 teams for Task 1 (22 runs) and seven teams for Task 2 (18 runs). On the statute law task, there were 9 different teams participating, most in more than one task. 6 teams submitted a total of 16 runs for Task 3, and 9 teams submitted a total of 26 runs for Task 4. We describe the variety of approaches, our official evaluation, and analysis of our data and submission results.

The automated translation of natural language text into structured logical representations is a critical task in various applications, including legal reasoning and decision-making. This paper presents a Name Entity Recognition (NER) based approach for translating the legal case descriptions written in natural language into PROLEG fact formulas. The approach comprises (1) extracting legal entities from the case description using a specialized NER model, namely LegalCaseNER and (2) transforming the extracted entities into PROLEG fact formulas using PROLEG rules. The experimental results demonstrate the efficacy of our proposed approach in accurately extracting relevant entities from legal case descriptions and translating them into the appropriate PROLEG fact formulas. Our approach provides a promising solution for handling complex and diverse case descriptions, enabling their representation in a structured format. This work provides a foundation for future research in the application of logical fact formulas in legal reasoning and decision-making.

Constraint programming is a powerful tool for modeling and solving various problems. Especially, soft constraints are useful since they enable the treatment of over-and under-constrained real-world problems by relaxing conflicting constraints and introducing default constraints. Constraint hierarchies provide a soft constraint framework that introduces hierarchical preferences called strengths. In a constraint hierarchy, constraints are associated with strengths such as required, strong, medium, and weak, and a solution is obtained to maximally satisfy stronger constraints in the sense of a given solution criterion. In this paper, we propose three methods based on binary search for solving constraint hierarchies over finite domains by using a criterion called unsatisfied-count-better. Our methods solve constraint hierarchies by encoding them into ordinary constraint satisfaction problems and repeatedly solving the encoded problems with an external solver. We also present the implementations of our methods and the results of the experiment that we conducted to evaluate them.

To exhaustively understand the impact of rule amendments and unforeseen cases on existing norms, it requires connecting their rule-based and case-based representations. However, those connections have not been explored in depth, especially for norms that are represented as soft constraints. This paper aims to explore the connection between constraint hierarchies and case models as representative formalisms of rule-based and case-based representations of soft-constraint norms respectively. To explore the connection, we express norm scopes and preferences in both formalisms as diagrams. Based on tightening and arranging diagrams, we found the translation of constraint hierarchies with one constraint per level into case models. This provides new insights into understanding prototypical cases made by rule-based soft-constraint norms.

Large Language Models (LLMs) face limitations in logical reasoning, which restrict their applicability in critical domains such as law. Current evaluation methods often lead to inaccurate assessments of LLMs’ capabilities due to their simplicity. This paper presents a refined evaluation method for assessing LLMs’ capability to answer legal questions by eliminating the possibility of obtaining correct responses by chance. Furthermore, we introduce the LogiLaw dataset, which aims to enhance the models’ logical reasoning capacities in general and legal reasoning specifically. By leveraging the refined evaluation technique, the LogiLaw dataset, and the proposed Reinforcement Learning from Logical Feedback (RLLF) approach, our work aims to open new avenues for research to bolster LLMs’ performance in law and other logic-intensive disciplines while addressing the shortcomings of conventional evaluation approaches.

We present LawGiBa, a proof-of-concept demonstration system for legal assistance that combines GPT, legal knowledge bases, and Prolog’s logic programming structure to provide explanations for legal queries. This novel combination effectively and feasibly addresses the hallucination issue of large language models (LLMs) in critical domains, such as law. Through this system, we demonstrate how incorporating a legal knowledge base and logical reasoning can enhance the accuracy and reliability of legal advice provided by AI models like GPT. Though our work is primarily a demonstration, it provides a framework to explore how knowledge bases and logic programming structures can be further integrated with generative AI systems, to achieve improved results across various natural languages and legal systems.

In the legal domain, extracting information from contracts poses significant challenges, primarily due to the scarcity of annotated data. In such situations, leveraging large language models (LLMs), such as the Generative Pretrained Transformer (GPT) models, offers a promising solution. However, the inherent token limitations of these models can be a bottleneck for processing lengthy legal contracts. This paper presents an unsupervised two-step approach to address these challenges. First, we propose a query-based summarization model that extracts sentences pertinent to predefined queries, concisely representing lengthy contracts. This summarization ensures that the core information remains intact while simultaneously addressing the token limitation issue. Subsequently, the generated summary is fed to GPT-3.5 for precise information extraction. Our approach effectively overcomes the challenges of token limitations and zero resources, enabling efficient and scalable information extraction from legal contracts. We compare our results with those obtained from supervised models that have been fine-tuned on domain-specific annotated data. Experimental results demonstrate the remarkable effectiveness of our approach, as it achieves state-of-the-art performance without the need for domain-specific training data.

This paper studies constraint hierarchies for ethical norms, which are unwritten and may be relaxed if they conflict with stronger norms. Since such ethical norms are unwritten, initial representations of ethical norms may contain errors. For correcting those errors, this paper examines fundamental revisions on constraint hierarchies for ethical norms. Although some revisions on representations for ethical norms have been suggested, revisions on constraint hierarchies for ethical norms have not been completely investigated. In this paper, we categorize two fundamental types of revisions on such constraint hierarchies, namely preference revision and content revision. We also compare effects of those revisions in the criteria of syntactic and semantic changes, which are common criteria of revisions on legal theories. From the comparison, we found that preference revision tentatively makes lower syntactic changes. However, its computation is intractable, incomplete, and potentially makes a large number of semantic changes. On the other hand, we show that content revision on constraint hierarchies can make a small number of semantic changes. However, the content revision tentatively produce a large number of syntactic changes. This comparison leads to the possibility of optimization between preference revision and content revision, which we think is an interesting future work.

Translating often has the meaning of converting from one human language to another. However, in a broader sense, it means transforming a message from one form of communication to another form. Logic is an important form of communication and the ability to translate natural language into logic is important in many different fields, in which logical reasoning and logical arguments are used. In the legal field, for example, judges must often reason from facts and arguments presented in natural language to logical conclusions. In this paper, toward the goal of support for this kind of reasoning with machines, we propose a method for translating natural language into logical representations using a combination of deep learning methods. Our approach contributes methodologies and insights to the development of computational methods for converting natural language into logical representations.

PROLEG is a famous computer program supporting attorneys in the legal inference process. However, the input of this system is expressed in Prolog, which most lawyers are not familiar with. This technical barrier is a serious problem for using PROLEG in the real legal context. A natural language interface is one of the solutions to this problem. We have developed a prototype of such an interface. This paper describes the prototype and its current performance. The prototype translates input facts into Prolog expressions following PROLEG syntax. The system consists of three main modules, (1) natural language perceiver, (2) PROLEG reasoner, and (3) inference explainer. In addition, we analyze the performance of the prototype and identify existing issues and discuss possible solutions.

It is challenging for lay consumers to predict a legal conclusion by applying appropriate law in a consumer dispute. We developed a system that assists consumers to predict a possible legal conclusion. The system enables consumers to identify the type of consumer disputes by using a tree structure, and to apply appropriate legal rules implemented as PROLEG programs. We arranged the system to avoid possible inconsistency between the tree structure and the PROLEG program.

When literal interpretation of statutes leads to counterintuitive consequences, judges, especially in high courts, may identify counterintuitive consequences and revise interpretation of statutes. Researchers have studied revisions for computational legal representation. Generally, studies on revision usually consider minimal revision to reflect limitation of judges' legislative power. However, those studies tend to minimize the number of operations used for changing rules rather than minimize the changes of semantics (the set of conclusions obtained from the program), which vary among cases. In this paper, we consider minimizing the changes of semantics of a rule-base written in a normal logic program. We consider that each possible fact-base (the representation of a case) has its corresponding semantics and corresponding dominant rule-base, which is a set of Horn clauses obtained from the subset of rule-base that is specific to the considered fact-base. Hence, we present a new sub type of semantics-based minimal revision called a dominant-based minimal revision. Furthermore, we present one guidance to obtain one dominant-based minimal revision by using legal debugging and Closed World Specification. We also compare the dominant-based minimal revision with the syntax-based minimal revision in Theory Distance Metric. As the syntax-based minimal revision minimizes the number of operations used for changing rules, the comparison shows that the syntax-based minimal revision may cause extra semantics changes compared to the dominant-based minimal revision, especially when the rule-base contains multiple rules for the same consequence. We discuss that such extra semantics changes can be considered as unintentional changes caused by the syntax-based minimal revision. Hence, legal reasoning systems can check with the user such extra semantics changes to confirm the user intention of changes.

In Japan, we have the procedure of "arranging issues" in civil litigation where we clarify which facts are in dispute and what kind of evidence action should be made for these issues. Currently, IT technology is used only for online meeting for arranging issues and more sophisticated method is expected by a full use of IT/AI technology.

Legal case retrieval is a specialized IR task that involves retrieving supporting cases given a query case. Compared with traditional ad-hoc text retrieval, the legal case retrieval task is more challenging since the query case is much longer and more complex than common keyword queries. Besides that, the definition of relevance between a query case and a supporting case is beyond general topical relevance and it is therefore difficult to construct a large-scale case retrieval dataset, especially one with accurate relevance judgments. To address these challenges, we propose BERT-PLI, a novel model that utilizes BERT to capture the semantic relationships at the paragraph-level and then infers the relevance between two cases by aggregating paragraph-level interactions. We fine-tune the BERT model with a relatively small-scale case law entailment dataset to adapt it to the legal scenario and employ a cascade framework to reduce the computational cost. We conduct extensive experiments on the benchmark of the relevant case retrieval task in COLIEE 2019. Experimental results demonstrate that our proposed method outperforms existing solutions.

Since the legal rules cannot be perfect, we have proposed a work called Legal Debugging for handling counterintuitive consequences caused by imperfection of the law. Legal debugging consists of two steps. Firstly, legal debugging interacts with a judge as an oracle that gives the intended interpretation of the law and collaboratively figures out a legal rule called a culprit, which determines as a root cause of counterintuitive consequences. Secondly, the legal debugging determines possible resolutions for a culprit . The way we have proposed to resolve a culprit is to use extra facts that have not been considered in the legal rules to describe the exceptional situation of the case. Nevertheless, the result of the resolution is usually considered as too specific and no generalizations of the resolution are provided. Therefore, in this paper, we introduce a rule generalization step into Legal Debugging. Specifically, we have reorganized Legal Debugging into four steps, namely a culprit detection, an exception invention, a fact-based induction, and a rule-based induction. During these four steps, a new introduced rule is specific at first then becomes more generalized. This new step allows a user to use existing legal concepts from the background knowledge for revising and generalizing legal rules.

We formalized renvoi in private international law in JURIX 2019 in terms of modal logic fragment. In this demonstration paper, we show an implementation of the formalism by translating modal formula into a logic program.

Abductive Logic Programming (ALP) has been proven very effective for formalizing societies of agents, commitments and norms, in particular by mapping the most common deontic operators (obligation, prohibition, permission) to abductive expectations. In our previous works, we have shown that ALP is a suitable framework for representing norms. Normative reasoning and query answering were accommodated by the same abductive proof procedure, named 𝒮CIFF. In this work, we introduce a defeasible flavour in this framework, in order to possibly discharge obligations in some scenarios. Abductive expectations can also be qualified as dischargeable, in the new, extended syntax. Both declarative and operational semantics are improved accordingly, and proof of soundness is given under syntax allowedness conditions Moreover, the dischargement itself might be proved invalid, or incoherent with the rules, due to new knowledge provided later on. In such a case, a discharged expectation might be reinstated and hold again after some evidence is given. We extend the notion of dischargement to take into consideration also the reinstatement of expectations. The expressiveness and power of the extended framework, named 𝒮CIFF𝒟, is shown by modeling and reasoning upon a fragment of the Japanese Civil Code. In particular, we consider a case study concerning manifestations of intention and their rescission (Section II of the Japanese Civil Code).

We present our method for tackling the legal case retrieval task of the Competition on Legal Information Extraction/Entailment 2019. Our approach is based on the idea that summarization is important for retrieval. On one hand, we adopt a summarization based model called encoded summarization which encodes a given document into continuous vector space which embeds the summary properties of the document. We utilize the resource of COLIEE 2018 on which we train the document representation model. On the other hand, we extract lexical features on different parts of a given query and its candidates. We observe that by comparing different parts of the query and its candidates, we can achieve better performance. Furthermore, the combination of the lexical features with latent features by the summarization-based method achieves even better performance. We have achieved the state-of-the-art result for the task on the benchmark of the competition.

The paper deals with the problem of formalizing the renvoi in private international law.A rule based (first-order) fragment of a multimodal logic including context modalities as well as a (simplified) notion of common knowledge is introduced.It allows context variables to occur within modalities and context names to be used as predicate arguments, providing a simple combination of meta-predicates and modal constructs.The nesting of contexts in queries is exploited in the formalization of the renvoi problem.

Generating from Abstract Meaning Representation (AMR) is a non-trivial problem, as many syntactic decisions are not constrained by the semantic graph. Current deep learning approaches in AMR generation almost depend on a large amount of "silver data" in general domains. While the text in the legal domain is often structurally complicated, and contain specific terminologies that are rarely seen in training data, making text generated from those deep learning models usually become awkward with lots of "out of vocabulary" tokens. In our paper, we propose some modifications in the training and decoding phase of the state of the art AMR generation model to have a better text realization. Our model is tested using a human-annotated legal dataset, showing an improvement compared to the baseline model.

Abstract Computer‐Interpretable Guidelines (CIGs) are the dominant medium for the delivery of clinical decision support, given the evidence‐based nature of their source material. Therefore, these machine‐readable versions have the ability to improve practitioner performance and conformance to standards, with availability at the point and time of care. The formalisation of Clinical Practice Guideline knowledge in a machine‐readable format is a crucial task to make it suitable for the integration in Clinical Decision Support Systems. However, the current tools for this purpose reveal shortcomings with respect to their ease of use and the support offered during CIG acquisition and editing. In this work, we characterise the current landscape of CIG acquisition tools based on the properties of guideline visualisation, organisation, simplicity, automation, manipulation of knowledge elements, and guideline storage and dissemination. Additionally, we describe the CompGuide Editor, a tool for the acquisition of CIGs in the CompGuide model for Clinical Practice Guidelines that also allows the editing of previously encoded guidelines. The Editor guides the users throughout the process of guideline encoding and does not require proficiency in any programming language. The features of the CIG encoding process are revealed through a comparison with already established tools for CIG acquisition.

Although recent advances of significant subgraph mining enable us to find subgraphs that are statistically significantly associated with the class variable from graph databases, it is challenging to interpret the resulting subgraphs due to their massive number and their propositional representation . Here we represent graphs by probabilistic logic programming and solve the problem of summarizing significant subgraphs by structure learning of probabilistic logic programs. Learning probabilistic logical models leads to a much more interpretable, expressive and succinct representation of significant subgraphs. We empirically demonstrate that our approach can effectively summarize significant subgraphs with keeping high accuracy.

This paper is concerned with the task of finding majority opinion (MO) in UK House of Lords (UKHL) case law by analysing agreement statements (AS) that explicitly express the appointed judges' acceptance of each other's reasoning. We introduce a corpus of 300 UKHL cases in which the relevant AS and MO have been annotated by three legal experts; and we introduce an AI system that automatically identifies this AS and MO with a performance comparable to humans.

Case-based reasoning (CBR) is extensively used in AI in support of several applications, to assess a new situation (or case) by recollecting past situations (or cases) and employing the ones most similar to the new situation to give the assessment. In this paper we study properties of a recently proposed method for CBR, based on instantiated Abstract Argumentation and referred to as AA-CBR, for problems where cases are represented by abstract factors and (positive or negative) outcomes, and an outcome for a new case, represented by abstract factors, needs to be established. In addition, we study properties of explanations in AA-CBR and define a new notion of lean explanations that utilize solely relevant cases. Both forms of explanations can be seen as dialogical processes between a proponent and an opponent, with the burden of proof falling on the proponent.

TropICAL is a Domain Specific Language (DSL) for the description of abstract legal policies. Taking inspiration from narrative tropes, our DSL enables the creation of component “policies” that may be reused between case descriptions. These components are compiled to social institutions, which are realised in Answer Set Programming (ASP) code. In this way, the actions of defendant and plaintiff take the shape of a story which must conform to the rules in the ASP description. We propose the use of our DSL in a tool designed for lawyers to generate arguments for the argumentation process.

The role of assistive technologies is to help users with diminished capabilities in the fulfillment of their everyday tasks. One of such tasks is orientation. It is crucial for the autonomy of an individual and, at the same time, it is one of the most challenging tasks for an individual with cognitive disabilities. Existing solutions that tackle this problem are mostly concerned with guidance, tracking and the display of information. However, there is a dimension that has not been the object of concern in existing projects, the prediction of user actions. This work presents a Speculative Module for an orientation system that is used to alert the user for potential mistakes in his path, anticipating possible shifts in the wrong direction in critical points of the route. With this module, it becomes possible to issue warnings to the user and increase his attention so as to avoid a deviation from the correct path.

Clinical Practice Guidelines, as evidence-based recommendations are the ideal support for Clinical Decision Support Systems. The intricacies of a guideline execution tool are related with the establishment of a care flow with an appropriate order between procedures and the modelling of decision points. One of such decision points is the choice between alternative tasks based on trigger conditions regarding a patient's state. It may be the case that, when there is the need to choose one of the alternative tasks, the system does not possess all the required information to do so, thus rendering impossible to reach an outcome. Speculative Computation and Abduction may increase the efficiency of this process by allowing the system to advance the computation of a solution, even while it is waiting for a response from the information sources. This work provides the basis for a Speculative Computation framework able to cope with decisions of clinical care flows. The methods developed herein were devised to support practitioners and to improve patient-centred medicine by providing maps of the most likely evolution of a patient, even when the information is incomplete.

Conflicts between laws can readily arise in situations governed by different laws, a case in point being when the context of an inferior law (or set of regulations) is altered through revision of a superior law. Being able to detect these conflicts automatically and resolve them, for example by proposing revisions to one of the modelled laws or policies, would be highly beneficial for legislators, legal departments of organizations or anybody having to incorporate legal requirements into their own procedures. In this paper we present a model based approach for detecting and finding legal conflicts through a combination of a formal model of legal specifications and a computational model based on answer set programming and inductive logic programming. Given specific scenarios (descriptions of courses of action), our model-based approach can automatically detect whether these scenarios could lead to contradictory outcomes in the different legal specifications. Using these conflicts as use cases, we apply inductive logic programming (ILP) to learn revisions to the legal component that is the source of the conflict. We illustrate our approach using a case-study where a university has to change its studentship programme after the government brings in new immigration regulations.

Acting under several jurisdictions at the same time is becoming the norm rather than the exception, certainly for companies but also (sometimes without knowing) for individuals. In these circumstances disparities among the different laws are inevitable. Here, we present a mathematical and a computational model of interacting legal specifications, along with a mechanism to find conflicts between them. We illustrate the approach by a case study using European Privacy law.

Abstract In this paper we propose a use-case-driven iterative design methodology for normative frameworks, also called virtual institutions, which are used to govern open systems. Our computational model represents the normative framework as a logic program under answer set semantics (ASP). By means of an inductive logic programming approach, implemented using ASP, it is possible to synthesise new rules and revise the existing ones. The learning mechanism is guided by the designer who describes the desired properties of the framework through use cases, comprising (i) event traces that capture possible scenarios, and (ii) a state that describes the desired outcome. The learning process then proposes additional rules, or changes to current rules, to satisfy the constraints expressed in the use cases. Thus, the contribution of this paper is a process for the elaboration and revision of a normative framework by means of a semi-automatic and iterative process driven from specifications of (un)desirable behaviour. The process integrates a novel and general methodology for theory revision based on ASP.

The Japanese “theory of presupposed ultimate facts” (called “Yoken-jijitsu-ron” in Japanese) for interpreting the Japanese civil code has been underway for over forty years mainly by judges in the Japanese Legal Training Institute, but not yet formalized in a mathematical way. This paper attempts to mathematically formalize this theory and presents the correspondence between the theory and logic programming with “negation as failure”. It is quite surprising that Japanese judges independently developed such a theory without knowing about logic programming.

This paper proposes several methods visualizing topics in documents, (i) Word Colony represents the dependency relationships among term occurrences in a target document. It helps users get an overview of a document. Using Word Colony with pictures gives users a more intuitive impression, (ii) topic sequence is a concatenation of Word Colonies for segmented documents. It shows plots as a story's topic transitions. (Hi) topic matrix represents relations among topics based on latent contexts within a collection of documents. Several visualization techniques enable users to visualize topics in a document in different ways. It gives variations of viewpoint and triggers the creative imagination.

This paper proposes a visualization tool, called Topic Tracer, to show topic transitions of not only a story existing in a document but also stories traversing over several documents. To visualize topic transition, first we have developed an analytical method to divide a document into parts. Then, we introduce a Word Colony to show topic terms in a whole or a part of document. It is a directed graph which shows the dependency relationships among terms occurrences in the target document. The Word Colony helps users to grasp the overview of a document. The concatenation of Word Colony gives plots of an existing story or crossing stories over several documents. This paper explains the concept and implementation of Topic Tracer using the minutes of the CUBE-SAT project, "Student-built Educational Pico-Satellite Design", in University of Tokyo

UML (unified modeling language) is the de facto standard model representation language in software engineering. We believe that automated contradiction detection and repair of UML become very important as UML has been widely used. In this paper, we propose a debugging system using logic programming paradigm for UML class diagram with class attributes, multiplicity, generalization relation and disjoint relation. We propose a translation method of a UML class diagram into a logic program, and using a meta-interpreter we can find (set-inclusion-based) minimal sets of rules which leads to contradiction. Then, we use a minimal hitting set algorithm developed by one of the authors to show minimal sets of deletion of rules in order to avoid contradiction