Legal Domain Research Articles

Neural Data Augmentation for Legal Overruling Task: Small Deep Learning Models vs. Large Language Models

Deep learning models produce impressive results in any natural language processing applications when given a better learning strategy and trained with large labeled datasets. However, the annotation of massive training data is far too expensive, especially in the legal domain, due to the need for trained legal professionals. Data augmentation solves the problem of learning without labeled big data. In this paper, we employ pre-trained language models and prompt engineering to generate large-scale pseudo-labeled data for the legal overruling task using 100 data samples. We train small recurrent and convolutional deep-learning models using this data and fine-tune a few other transformer models. We then evaluate the effectiveness of the models, both with and without data augmentation, using the benchmark dataset and analyze the results. We also test the performance of these models with the state-of-the-art GPT-3 model under few-shot setting. Our experimental findings demonstrate that data augmentation results in better model performance in the legal overruling task than models trained without augmentation. Furthermore, our best-performing deep learning model trained on augmented data outperforms the few-shot GPT-3 by 18% in the F1-score. Additionally, our results highlight that the small neural networks trained with augmented data achieve outcomes comparable to those of other large language models.

Artificial Intelligence-based Legal Application for Resolving Issues Related to Live-In Relationship

INTRODUCTION: The societal landscape in India has witnessed a very transformative shift in the perspectives on relationships, with an increasing prevalence of live-in couples challenging the traditional norms of marriage. However, this ongoing trend has brought about a huge surge in legal complexities, including recognition, partner rights, property disputes, and inheritance issues. This study proposed an innovative approach that leveraged the potential of Artificial Intelligence and Automatic speech recognition for the registration and redressal of live-in relationship matters.
 OBJECTIVES: This research explores and seeks for the optimization of the resolution of live-in relationship disputes which occurs in the legal perspective with the help of an AI-based platform. The primary goal of this research was to overcome the physical barriers while ensuring the correct accessibility to legal procedures for the registration and addressing of the grievances related to live-in relationships. 
 METHODS: Here, the methodology followed, starting from the thorough review which was conducted using different resources from Scopus, PubMed, and ResearchGate. This research explored the increasing complaints and varying victim counts in live-in relationship cases. This finally attributed to these issues to a lack of physical access to legal remedies.
 RESULTS: This study also emphasized the major significance of AI-driven redressal processes in the real-time alleviation of the hurdles and challenges associated with live-in relationship cases. The proposed framework and platform aimed to offer an alternative means for the individuals who were unable to physically approach the authorities, facilitating a more efficient and seamless way of legal resolution more quickly.
 CONCLUSION: This study advocates for the integration of AI and AST technologies in the legal domain, specifically for addressing live-in relationship issues. The implementation of such a system had the potential to bridge gaps in its accessibility, thereby contributing to a more inclusive and efficient legal framework for individuals who are passionately involved in live-in relationships.

Regulatory requirement for Medical Devices

The safety and regulatory compliance of a widely used medical device have become a growing concern among a significant population. This has raised questions about the assessment of risks, monitoring of adverse drug reactions (ADR), and overall product safety. The efficacy and safety of such medical devices heavily rely on the regulations and guidelines set forth by regulatory agencies (RAs).
 In the pharmaceutical industry, regulatory affairs (RA) professionals play a crucial role in overseeing the lifecycle of healthcare products. They provide strategic, tactical, and operational guidance to ensure compliance with regulations, facilitating the efficient development and delivery of safe and effective healthcare products worldwide. Evaluating adherence to regulations requires a combination of expertise from the business, legal, and pharmaceutical domains.
 Regulatory authorities must thoroughly monitor medical device design, development, and manufacturing processes to guarantee that the products reaching the market are safe and effective. The certification process is intricate, involving multiple steps and the assessment of materials by competent authorities. In the United States, manufacturers must seek marketing authorization from the United States Food and Drug Administration (USFDA) through two primary application types: 510(k) and Pre-Market Application (PMA). In the European Union (EU), national authorities grant permission for the sale of medical devices, employing a third-party compliance system where notified bodies ensure quality assurance pre- and post-approval. In India, the Central Drug Standard Control Organization (CDSCO) licenses devices for sale and import under the CLAA framework.
 Conclusion
 Pharmaceutical regulatory affairs experts play a critical role in ensuring compliance with industry requirements for all pharmaceutical products. This review provides an overview of how medical devices are regulated and monitored in the EU, India, and the USA, emphasizing the importance of regulatory affairs in maintaining the safety and efficacy of healthcare products.

A SURVEY ON SUMMARIZATION OF LEGAL TEXTS

The task of summarizing legal texts is of paramount importance in facilitating access to legal knowledge. This survey paper critically reviews and analyzes diverse methodologies applied to the challenging task of summarizing legal texts. In the supervised realm, models such as GIST, SummaRuNNer, and BERTSUM have gained prominence, demonstrating prowess in extractive summarization techniques. Semi-supervised methods, leveraging innovative techniques such as TF-IDF Scores and Sentence Embeddings, have proven effective in handling the intricate structure of court judgments. Unsolicited approaches, CaseSummarizer and exemplified by USLT-LEGAL-BERT, address the challenges of summarization without the luxury of labeled data, showcasing their adaptability to diverse legal domains. Furthermore, the paper explores legal document retrieval strategies, incorporating document vector embeddings and deep learning techniques, underscoring the significance of domain-specific approaches. The study encompasses a variety of models, from Legal-BERT to hierarchical encoder decoder frameworks, showcasing their applicability in handling the complexity inherent in legal texts. Additionally, the survey delves into BERT-based techniques for legal classification tasks, emphasizing the crucial role of context and introducing innovative methods such as "Stride 64." In the realm of legal text simplification, the survey scrutinizes the KIS model and graph-based approaches, revealing nuanced trade- offs between readability, fluency, and meaning preservation. The research culminates with an exploration of the team's participation in LegalEval 2023 shared tasks, underscoring the prowess of deep learning models in tasks such as rhetorical role classification and legal named entity extraction.This survey paper provides a nuanced and comprehensive perspective on the evolving landscape of legal document summarization, offering valuable insights into current methodologies, challenges, and potential future directions for advancing the field. Keywords- Legal text Summarization,Supervised Learning, Extractive Summarization,Semi-supervised methods,Deep learning Techniques,Legal Document retrieval.

Legality of Blockchain and Smart Contracts in India

India is presently experiencing a moment of profound transformation that encompasses revisions to its constitution and legal principles. In this era of remarkable transformation, it would be imprudent to overlook the technological innovations and digital advancements that have permeated the legal domain. One particularly vital aspect in this context is the field of Contract Law. Presently, electronic contracts in India are primarily governed by The Indian Contract Act, in conjunction with the Information Technology Act and the Indian Evidence Act, unless stated otherwise. These legal frameworks provide the foundation for legally enforceable electronic contracts in the country. This research paper emphasizes the urgent requirement for a legal adaptation in the field of Contract Law to align with the ever-evolving technological landscape. It also delves into the legal intricacies associated with blockchain-based Smart Contracts, elucidating how these contracts function within the current judicial landscape. Finally, it concludes by emphasizing the necessity for a pioneering effort to regulate this dynamic domain.

Revolutionizing Legal Assistance: A Comprehensive Survey on the Development and Implementation of a Personalized Legal Guidance Android Application

This detailed overview investigates the innovative progression and execution of a revolutionary Personalized Legal Guidance Android Application. Through the utilization of cutting-edge technology, advanced algorithms, and a user-focused design, the application aims to redefine individuals’ interactions with legal information. The paper methodically examines the essential features, technological components, user experience, and potential implications on the legal domain, providing a holistic perspective on this transformative legal advancement. Keywords: Personalized Legal Guidance, Android Application, Technology, Legal Landscape, User Experience.

Editorial: Language and Law

Initiated against the backdrop of the NWU Faculty of Law's inaugural "Justice in Practice" colloquium in March 2022, this collection of articles represents an independent and meticulously scrutinised body of work. While inspired by the colloquium's overarching theme, each contribution has undergone a rigorous, blind peer review process, ensuring scholarly rigor and individual merit. The colloquium served as a catalyst for exploring unchartered territories in language and law research, emphasising the global South's unique perspective enriched by multilingualism and multiculturalism. In the complex tapestry of human society, the dynamic interplay between language and the legal domain emerges as a dynamic and evolving field demanding scholarly exploration and understanding.

Advancing Legal Citation Text Classification A Conv1D-Based Approach for Multi-Class Classification

The escalating volume and intricacy of legal documents necessitate advanced techniques for automated text classification in the legal domain. Our proposed approach leverages Convolutional Neural Networks (Conv1D), a neural network architecture adept at capturing hierarchical features in sequential data. The incorporation of max-pooling facilitates the extraction of salient features, while softmax activation enables the model to handle the multi-class nature of legal citation categorization. By addressing the limitations identified in previous studies, our model aims to advance the state-of-the-art in legal citation text classification, offering a robust and efficient solution for automated categorization in the legal domain. Our research contributes to the ongoing evolution of NLP applications in the legal field, promising enhanced accuracy and adaptability in the automated analysis of legal texts.

Performance, Energy Consumption and Costs: A Comparative Analysis of Automatic Text Classification Approaches in the Legal Domain

The common practice in Machine Learning research is to evaluate the top-performing models based on their performance. However, this often leads to overlooking other crucial aspects that should be given careful consideration. In some cases, the performance differences between various approaches may be insignificant, whereas factors like production costs, energy consumption, and carbon footprint should be taken into account. Large Language Models (LLMs) are widely used in academia and industry to address NLP problems. In this study, we present a comprehensive quantitative comparison between traditional approaches (SVM-based) and more recent approaches such as LLM (BERT family models) and generative models (GPT2 and LLAMA2), using the LexGLUE benchmark. Our evaluation takes into account not only performance parameters (standard indices), but also alternative measures such as timing, energy consumption and costs, which collectively contribute to the carbon footprint. To ensure a complete analysis, we separately considered the prototyping phase (which involves model selection through training-validation-test iterations) and the in-production phases. These phases follow distinct implementation procedures and require different resources. The results indicate that simpler algorithms often achieve performance levels similar to those of complex models (LLM and generative models), consuming much less energy and requiring fewer resources. These findings suggest that companies should consider additional considerations when choosing machine learning (ML) solutions. The analysis also demonstrates that it is increasingly necessary for the scientific world to also begin to consider aspects of energy consumption in model evaluations, in order to be able to give real meaning to the results obtained using standard metrics (Precision, Recall, F1 and so on).

Legal hypergraphs.

Complexity science provides a powerful framework for understanding physical, biological and social systems, and network analysis is one of its principal tools. Since many complex systems exhibit multilateral interactions that change over time, in recent years, network scientists have become increasingly interested in modelling and measuring dynamic networks featuring higher-order relations. At the same time, while network analysis has been more widely adopted to investigate the structure and evolution of law as a complex system, the utility of dynamic higher-order networks in the legal domain has remained largely unexplored. Setting out to change this, we introduce temporal hypergraphs as a powerful tool for studying legal network data. Temporal hypergraphs generalize static graphs by (i) allowing any number of nodes to participate in an edge and (ii) permitting nodes or edges to be added, modified or deleted. We describe models and methods to explore legal hypergraphs that evolve over time and elucidate their benefits through case studies on legal citation and collaboration networks that change over a period of more than 70 years. Our work demonstrates the potential of dynamic higher-order networks for studying complex legal systems, and it facilitates further advances in legal network analysis. This article is part of the theme issue 'A complexity science approach to law and governance'.

Towards human-centred standards for legal help AI.

As more groups consider how AI may be used in the legal sector, this paper envisions how companies and policymakers can prioritize the perspective of community members as they design AI and policies around it. It presents findings of structured interviews and design sessions with community members, in which they were asked about whether, how, and why they would use AI tools powered by large language models to respond to legal problems like receiving an eviction notice. The respondents reviewed options for simple versus complex interfaces for AI tools, and expressed how they would want to engage with an AI tool to resolve a legal problem. These empirical findings provide directions that can counterbalance legal domain experts' proposals about the public interest around AI, as expressed by attorneys, court officials, advocates and regulators. By hearing directly from community members about how they want to use AI for civil justice tasks, what risks concern them, and the value they would find in different kinds of AI tools, this research can ensure that people's points of view are understood and prioritized, rather than only domain experts' assertions about people's needs and preferences around legal help AI. This article is part of the theme issue 'A complexity science approach to law and governance'.

Reflections about Blockchain in Health Data Sharing: Navigating a Disruptive Technology.

A comprehensive analysis was performed, considering blockchain technology (BT) properties in digital health, addressing medicolegal, privacy, and regulatory considerations. Adherence to personal data protection and healthcare regulatory guidelines were analyzed and compared for GDPR (Europe), HIPAA (United States), CCPA (California), PIPEDA (Canada), the Privacy Act of 1988 (Australia), APPI (Japan), and LGPD (Brazil). Issues such as health systems, strengthening and aligning policy orientations and initiatives, and emphasizing the role of data analysis in shaping health policies were explored. The study addressed conflicts between the legal frameworks and blockchain, comparing and suggesting solutions like the revision of laws and the integration of compliance mechanisms. Additionally, it sought to enhance IT-health literacy by integrating the healthcare and legal domains. Ongoing collaboration between legal, health, and IT experts is essential for designing systems that effectively balance privacy rights and data protection while maximizing the benefits of disruptive technologies like blockchain.

Critical Psychology and the Brain: Rethinking Free will in the Legal Context.

The article draws from critical psychology to discuss the rising debate on brain determinism and free will in the legal domain. As free will also corresponds to the context and culture, it can have both the public and private space of expressions. The rise of neuroscience and its influence in the legal domain offers a holistic and sociocultural meaning of responsibility. Even one becomes entitled to take free will as a 'necessary illusion' in order to be in the zone of 'moral as well as legal-social life forming activities'. In the criminal justice system free will is not taken as any kind of 'necessary illusion' but the conscious will and action of the person. This further throw light on how the wilful control of any criminal act is a social act and our brain is not separate from our collective will.

Measuring and Mitigating Gender Bias in Legal Contextualized Language Models

Transformer-based contextualized language models constitute the state-of-the-art in several natural language processing (NLP) tasks and applications. Despite their utility, contextualized models can contain human-like social biases, as their training corpora generally consist of human-generated text. Evaluating and removing social biases in NLP models has been a major research endeavor. In parallel, NLP approaches in the legal domain, namely, legal NLP or computational law, have also been increasing. Eliminating unwanted bias in legal NLP is crucial, since the law has the utmost importance and effect on people. In this work, we focus on the gender bias encoded in BERT-based models. We propose a new template-based bias measurement method with a new bias evaluation corpus using crime words from the FBI database. This method quantifies the gender bias present in BERT-based models for legal applications. Furthermore, we propose a new fine-tuning-based debiasing method using the European Court of Human Rights (ECtHR) corpus to debias legal pre-trained models. We test the debiased models’ language understanding performance on the LexGLUE benchmark to confirm that the underlying semantic vector space is not perturbed during the debiasing process. Finally, we propose a bias penalty for the performance scores to emphasize the effect of gender bias on model performance.

A dynamic approach for visualizing and exploring concept hierarchies from textbooks.

In this study, we propose a visualization technique to explore and visualize concept hierarchies generated from a textbook in the legal domain. Through a human-centered design process, we developed a tool that allows users to effectively navigate through and explore complex hierarchical concepts in three kinds of traversal techniques: top-down, middle-out, and bottom-up. Our concept hierarchies offer an overview over a given domain, with increasing level of detail toward the bottom of the hierarchy which is consisting of entities. In the legal use case we considered, the concepts were adapted from section headings in a legal textbook, whereas references to law or legal cases inside the textbook became entities. The design of this tool is refined following various steps such as gathering user needs, pain points of an existing visualization, prototyping, testing, and refining. The resulting interface offers users several key features such as dynamic search and filter, explorable concept nodes, and a preview of leaf nodes at every stage. A high-fidelity prototype was created to test our theory and design. To test our concept, we used the System Usability Scale as a way to measure the prototype's usability, a task-based survey to asses the tool's ability in assisting users in gathering information and interacting with the prototype, and finally mouse tracking to understand user interaction patterns. Along with this, we gathered audio and video footage of users when participating in the study. This footage also helped us in getting feedback when the survey responses required further information. The data collected provided valuable insights to set the directions for extending this study. As a result, we have accounted for varying hierarchy depths, longer text spans than only one to two words in the elements of the hierarchy, searchability, and exploration of the hierarchies. At the same time, we aimed for minimizing visual clutter and cognitive overload. We show that existing approaches are not suitable to visualize the type of data which we support with our visualization.

The Precautionary Approach Design Pattern

The precautionary approach is a way to manage problems related to the uncertainty of scientific knowledge regarding potential serious harms and to enable decision-making under uncertainty with due diligence. I have developed a model of the essential structural elements of the application of the precautionary approach, particularly the precautionary principle in EU law, as a legal design pattern—a formalized presentation of the core generic features and processes of how the law successfully addresses recurring problems. The precautionary approach appears as a decision tree with weighting and balancing. It serves as an intervening rule to resolve inter-system conflicts between different action systems such as the economy, civil society, and ecological systems. It is related to other design patterns like the proportionality test, risk and impact assessment, and judicial review. Presenting the application of the precautionary approach as a legal design pattern facilitates interdisciplinary communication regarding the essential features of legally required problem-solving. Such a presentation enhances the problem-solving capacity of the application of the law beyond the legal domain, for instance, in improving digitalization efforts and enabling the integration of anticipatory quality controls of justice, legality and good governance into decision-making processes.

A Survey on Challenges and Advances in Natural Language Processing with a Focus on Legal Informatics and Low-Resource Languages

The field of Natural Language Processing (NLP) has experienced significant growth in recent years, largely due to advancements in Deep Learning technology and especially Large Language Models. These improvements have allowed for the development of new models and architectures that have been successfully applied in various real-world applications. Despite this progress, the field of Legal Informatics has been slow to adopt these techniques. In this study, we conducted an extensive literature review of NLP research focused on legislative documents. We present the current state-of-the-art NLP tasks related to Law Consolidation, highlighting the challenges that arise in low-resource languages. Our goal is to outline the difficulties faced by this field and the methods that have been developed to overcome them. Finally, we provide examples of NLP implementations in the legal domain and discuss potential future directions.

Predicting Critical Path of Labor Dispute Resolution in Legal Domain by Machine Learning Models Based on SHapley Additive exPlanations and Soft Voting Strategy

The labor dispute is one of the most common civil disputes. It can be resolved in the order of the following steps, which include mediation in arbitration, arbitration award, first-instance mediation, first-instance judgment, and second-instance judgment. The process can cease at any step when it is successfully resolved. In recent years, due to the increasing rights awareness of employees, the number of labor disputes has been rising annually. However, resolving labor disputes is time-consuming and labor-intensive, which brings a heavy burden to employees and dispute resolution institutions. Using artificial intelligence algorithms to identify and predict the critical path of labor dispute resolution is helpful for saving resources and improving the efficiency of, and reducing the cost of dispute resolution. In this study, a machine learning approach based on Shapley Additive exPlanations (SHAP) and a soft voting strategy is applied to predict the critical path of labor dispute resolution. We name our approach LDMLSV (stands for Labor Dispute Machine Learning based on SHapley additive exPlanations and Voting). This approach employs three machine learning models (Random Forest, Extra Trees, and CatBoost) and then integrates them using a soft voting strategy. Additionally, SHAP is used to explain the model and analyze the feature contribution. Based on the ranking of feature importance obtained from SHAP and an incremental feature selection method, we obtained an optimal feature subset comprising 33 features. The LDMLSV achieves an accuracy of 0.90 on this optimal feature subset. Therefore, the proposed approach is a highly effective method for predicting the critical path of labor dispute resolution.

Legal Information Retrieval and Entailment Using Transformer-based Approaches.

The challenge of information overload in the legal domain increases every day. The COLIEE competition has created four challenge tasks that are intended to encourage the development of systems and methods to alleviate some of that pressure: a case law retrieval (Task 1) and entailment (Task 2), and a statute law retrieval (Task 3) and entailment (Task 4). Here we describe our methods for Task 1 and Task 4. In Task 1, we used a sentence-transformer model to create a numeric representation for each case paragraph. We then created a histogram of the similarities between a query case and a candidate case. The histogram is used to build a binary classifier that decides whether a candidate case should be noticed or not. In Task 4, our approach relies on fine-tuning a pre-trained DeBERTa large language model (LLM) trained on SNLI and MultiNLI datasets. Our method for Task 4 was ranked third among eight participating teams in the COLIEE 2023 competition. For Task 4, We also compared the performance of the DeBERTa model with those of a knowledge distillation model and ensemble methods including Random Forest and Voting.

Mapping the Regulatory Framework for Telemedicine in Zambia: A Content Analysis

This paper explores the regulatory framework for telemedicine in Zambia. Telemedicine, involving remote clinical services using technology, is a rapidly evolving field intersecting with legal, ethical, and professional domains. The primary aim is to understand Zambia's telemedicine regulatory framework through an analysis of key documents namely the Zambia E-Government Interoperability Standard (eGIF), Zambia Digital Health Strategy 2022-2026, HPCZ Guidelines for the Quality Assurance of Telemedicine Services, and Statutory Instrument 43 of 2023 (SI 43 of 2023). The study addresses the challenge of comprehensively understanding and effectively implementing telemedicine in Zambia, considering the evolving nature of technology and healthcare services. Mapping the regulatory framework is a critical exercise for ensuring legal compliance, maintaining high standards of service, protecting patients, and making informed strategic decisions in the telemedicine sector. The study conducts a detailed exploration and content analysis of the aforementioned documents. This includes examination of their contributions to establishing a strong telemedicine landscape in Zambia, focusing on aspects like interoperability, data security, and healthcare service delivery. Findings reveal each document's significant, yet varied, contributions to the telemedicine framework in Zambia. The eGIF ensures integrated, standardized, and secure digital telemedicine services. The Zambia Digital Health Strategy 2022-2026 promotes telemedicine via digital technology and global alignment, while the HPCZ Guidelines provide a detailed framework focusing on ethical and legal standards. SI. 43 of 2023 emphasizes data security, quality assurance, and collaboration in telemedicine. Comparatively, Zambia's framework, as shaped by the four documents, aligns with global standards but differs in its centralized regulation and strategic focus, lacking extensive coverage on medical device regulations and reimbursement issues seen in other countries. The study suggests the need for a unified approach to telemedicine, emphasizing standardization, legal compliance, accessibility, and inclusivity. Recommendations include improving interoperability, ensuring data security, and fostering user-centric telemedicine services for enhanced healthcare outcomes.