Artificial Intelligence and Law最新文献

The Toulmin model has been proved useful in law and argumentation theory. This model describes the basic process in justifying a claim, which comprises six elements, i.e., claim (C), data (D), warrant (W), backing (B), qualifier (Q), and rebuttal (R). Specifically, in justifying a claim, one must put forward ‘data’ and a ‘warrant’, whereas the latter is authorized by ‘backing’. The force of the ‘claim’ being justified is represented by the ‘qualifier’, and the condition under which the claim cannot be justified is represented as the ‘rebuttal’. To further improve the model, (Goodnight, Informal Logic 15:41–52, 1993) points out that the selection of a backing needs justification, which he calls legitimation justification. However, how such justification is constituted has not yet been clarified. To identify legitimation justification, we separate it into two parts. One justifies a backing’s eligibility (legitimation justification₁; LJ₁); the other justifies its superiority over other eligible backings (legitimation justification₂; LJ₂). In this paper, we focus on LJ₁ and apply it to the legal justification (of judgements) in hard cases for illustration purposes. We submit that LJ₁ refers to the justification of the legal interpretation of a norm by its backing, which can be further separated into several orderable subjustifications. Taking the subjustification of a norm’s existence as an example, we show how it would be influenced by different positions in the philosophy of law. Taking the position of the theory of natural law, such subjustification is presented and evaluated. This paper aims not only to inform ongoing theoretical efforts to apply the Toulmin model in the legal field, but it also seeks to clarify the process in the justification of legal judgments in hard cases. It also offers background information for the possible construction of related AI systems. In our future work, LJ₂ and other subjustifications of LJ₁ will be discussed.

In the digital age, the use of advanced technology is becoming a new paradigm in police work, criminal justice, and the penal system. Algorithms promise to predict delinquent behaviour, identify potentially dangerous persons, and support crime investigation. Algorithm-based applications are often deployed in this context, laying the groundwork for a ‘smart criminal justice’. In this qualitative study based on 32 interviews with criminal justice and police officials, we explore the reasons why and extent to which such a smart criminal justice system has already been established in Switzerland, and the benefits perceived by users. Drawing upon this research, we address the spread, application, technical background, institutional implementation, and psychological aspects of the use of algorithms in the criminal justice system. We find that the Swiss criminal justice system is already significantly shaped by algorithms, a change motivated by political expectations and demands for efficiency. Until now, algorithms have only been used at a low level of automation and technical complexity and the levels of benefit perceived vary. This study also identifies the need for critical evaluation and research-based optimization of the implementation of advanced technology. Societal implications, as well as the legal foundations of the use of algorithms, are often insufficiently taken into account. By discussing the main challenges to and issues with algorithm use in this field, this work lays the foundation for further research and debate regarding how to guarantee that ‘smart’ criminal justice is actually carried out smartly.

This paper reflects my address as IAAIL president at ICAIL 2021. It is aimed to give my vision of the status of the AI and Law discipline, and possible future perspectives. In this respect, I go through different seasons of AI research (of AI and Law in particular): from the Winter of AI, namely a period of mistrust in AI (throughout the eighties until early nineties), to the Summer of AI, namely the current period of great interest in the discipline with lots of expectations. One of the results of the first decades of AI research is that “intelligence requires knowledge”. Since its inception the Web proved to be an extraordinary vehicle for knowledge creation and sharing, therefore it’s not a surprise if the evolution of AI has followed the evolution of the Web. I argue that a bottom-up approach, in terms of machine/deep learning and NLP to extract knowledge from raw data, combined with a top-down approach, in terms of legal knowledge representation and models for legal reasoning and argumentation, may represent a promotion for the development of the Semantic Web, as well as of AI systems. Finally, I provide my insight in the potential of AI development, which takes into account technological opportunities and theoretical limits.

In this paper, we discuss previous research in automatic prediction of court decisions. We define the difference between outcome identification, outcome-based judgement categorisation and outcome forecasting, and review how various studies fall into these categories. We discuss how important it is to understand the legal data that one works with in order to determine which task can be performed. Finally, we reflect on the needs of the legal discipline regarding the analysis of court judgements.

We define a formal semantics of conditionals based on normatively ideal worlds. Such worlds are described informally by Armgardt (Gabbay D, Magnani L, Park W, Pietarinen A-V (eds) Natural arguments: a tribute to john woods, College Publications, London, pp 699–708, 2018) to address well-known problems of the counterfactual approach to causation. Drawing on Armgardt’s proposal, we use iterated conditionals in order to analyse causal relations in scenarios of multi-agent interaction. This results in a refined counterfactual approach to causal responsibility in legal contexts, which solves overdetermination problems in an intuitively accessible manner.

Modelling that exploits visual elements and information visualisation are important areas that have contributed immensely to understanding and the computerisation advancements in many domains and yet remain unexplored for the benefit of the law and legal practice. This paper investigates the challenge of modelling and expressing structures and processes in legislation and the law by using visual modelling and information visualisation (InfoVis) to assist accessibility of legal knowledge, practice and knowledge formalisation as a basis for legal AI. The paper uses a subset of the well-defined Unified Modelling Language (UML) to visually express the structure and process of the legislation and the law to create visual flow diagrams called lawmaps, which form the basis of further formalisation. A lawmap development methodology is presented and evaluated by creating a set of lawmaps for the practice of conveyancing and the Landlords and Tenants Act 1954 of the United Kingdom. This paper is the first of a new breed of preliminary solutions capable of application across all aspects, from legislation to practice; and capable of accelerating development of legal AI.

Autonomous artificial intelligence (AI) systems can lead to unpredictable behavior causing loss or damage to individuals. Intricate questions must be resolved to establish how courts determine liability. Until recently, understanding the inner workings of “black boxes” has been exceedingly difficult; however, the use of Explainable Artificial Intelligence (XAI) would help simplify the complex problems that can occur with autonomous AI systems. In this context, this article seeks to provide technical explanations that can be given by XAI, and to show how suitable explanations for liability can be reached in court. It provides an analysis of whether existing liability frameworks, in both civil and common law tort systems, with the support of XAI, can address legal concerns related to AI. Lastly, it claims their further development and adoption should allow AI liability cases to be decided under current legal and regulatory rules until new liability regimes for AI are enacted.

The standard approach for abstractive text summarization is to use an encoder-decoder architecture. The encoder is responsible for capturing the general meaning from the source text, and the decoder is in charge of generating the final text summary. While this approach can compose summaries that resemble human writing, some may contain unrelated or unfaithful information. This problem is called “hallucination” and it represents a serious issue in legal texts as legal practitioners rely on these summaries when looking for precedents, used to support legal arguments. Another concern is that legal documents tend to be very long and may not be fed entirely to the encoder. We propose our method called LegalSumm for addressing these issues by creating different “views” over the source text, training summarization models to generate independent versions of summaries, and applying entailment module to judge how faithful these candidate summaries are with respect to the source text. We show that the proposed approach can select candidate summaries that improve ROUGE scores in all metrics evaluated.

The task of rhetorical role labeling is to assign labels (such as Fact, Argument, Final Judgement, etc.) to sentences of a court case document. Rhetorical role labeling is an important problem in the field of Legal Analytics, since it can aid in various downstream tasks as well as enhances the readability of lengthy case documents. The task is challenging as case documents are highly various in structure and the rhetorical labels are often subjective. Previous works for automatic rhetorical role identification (i) mainly used Conditional Random Fields over manually handcrafted features, and (ii) focused on certain law domains only (e.g., Immigration cases, Rent law), and a particular jurisdiction/country (e.g., US, Canada, India). In this work, we improve upon the prior works on rhetorical role identification by proposing novel Deep Learning models for automatically identifying rhetorical roles, which substantially outperform the prior methods. Additionally, we show the effectiveness of the proposed models over documents from five different law domains, and from two different jurisdictions—the Supreme Court of India and the Supreme Court of the UK. Through extensive experiments over different variations of the Deep Learning models, including Transformer models based on BERT and LegalBERT, we show the robustness of the methods for the task. We also perform an extensive inter-annotator study and analyse the agreement of the predictions of the proposed model with the annotations by domain experts. We find that some rhetorical labels are inherently hard/subjective and both law experts and neural models frequently get confused in predicting them correctly.