Hybrid search has emerged as an effective strategy to offset the limitations of different matching paradigms, especially in out-of-domain contexts where notable improvements in retrieval quality have been observed. However, existing research predominantly focuses on a limited set of retrieval methods, evaluated in pairs on domain-general datasets exclusively in English. In this work, we study the efficacy of hybrid search across a variety of prominent retrieval models within the unexplored field of law in the French language, assessing both zero-shot and in-domain scenarios. Our findings reveal that in a zero-shot context, fusing different domain-general models consistently enhances performance compared to using a standalone model, regardless of the fusion method. Surprisingly, when models are trained in-domain, we find that fusion generally diminishes performance relative to using the best single system, unless fusing scores with carefully tuned weights. These novel insights, among others, expand the applicability of prior findings across a new field and language, and contribute to a deeper understanding of hybrid search in non-English specialized domains.

State-of-the-art neural retrievers predominantly focus on high-resource languages like English, which impedes their adoption in retrieval scenarios involving other languages. Current approaches circumvent the lack of high-quality labeled data in non-English languages by leveraging multilingual pretrained language models capable of cross-lingual transfer. However, these models require substantial task-specific fine-tuning across multiple languages, often perform poorly in languages with minimal representation in the pretraining corpus, and struggle to incorporate new languages after the pretraining phase. In this work, we present a novel modular dense retrieval model that learns from the rich data of a single high-resource language and effectively zero-shot transfers to a wide array of languages, thereby eliminating the need for language-specific labeled data. Our model, ColBERT-XM, demonstrates competitive performance against existing state-of-the-art multilingual retrievers trained on more extensive datasets in various languages. Further analysis reveals that our modular approach is highly data-efficient, effectively adapts to out-of-distribution data, and significantly reduces energy consumption and carbon emissions. By demonstrating its proficiency in zero-shot scenarios, ColBERT-XM marks a shift towards more sustainable and inclusive retrieval systems, enabling effective information accessibility in numerous languages.

Understanding the legally relevant factual basis of an event and conveying it through text is a key skill of legal professionals. This skill is important for preparing forms (e.g., insurance claims) or other legal documents (e.g., court claims), but often presents a challenge for laypeople. Current AI approaches aim to bridge this gap, but mostly rely on the user to articulate what has happened in text, which may be challenging for many. Here, we investigate the capability of large language models (LLMs) to understand and summarize events occurring in videos. We ask an LLM to summarize and draft legal letters, based on 120 YouTube videos showing legal issues in various domains. Overall, 71.7% of the summaries were rated as of high or medium quality, which is a promising result, opening the door to a number of applications in e.g. access to justice.

Many individuals are likely to face a legal dispute at some point in their lives, but their lack of understanding of how to navigate these complex issues often renders them vulnerable. The advancement of natural language processing opens new avenues for bridging this legal literacy gap through the development of automated legal aid systems. However, existing legal question answering (LQA) approaches often suffer from a narrow scope, being either confined to specific legal domains or limited to brief, uninformative responses. In this work, we propose an end-to-end methodology designed to generate long-form answers to any statutory law questions, utilizing a "retrieve-then-read" pipeline. To support this approach, we introduce and release the Long-form Legal Question Answering (LLeQA) dataset, comprising 1,868 expert-annotated legal questions in the French language, complete with detailed answers rooted in pertinent legal provisions. Our experimental results demonstrate promising performance on automatic evaluation metrics, but a qualitative analysis uncovers areas for refinement. As one of the only comprehensive, expert-annotated long-form LQA dataset, LLeQA has the potential to not only accelerate research towards resolving a significant real-world issue, but also act as a rigorous benchmark for evaluating NLP models in specialized domains. We publicly release our code, data, and models.

The anonymity on the Darknet allows vendors to stay undetected by using multiple vendor aliases or frequently migrating between markets.Consequently, illegal markets and their connections are challenging to uncover on the Darknet.To identify relationships between illegal markets and their vendors, we propose Ven-dorLink, an NLP-based approach that examines writing patterns to verify, identify, and link unique vendor accounts across text advertisements (ads) on seven public Darknet markets.In contrast to existing literature, VendorLink utilizes the strength of supervised pre-training to perform closed-set vendor verification, openset vendor identification, and low-resource market adaption tasks.Through VendorLink, we uncover (i) 15 migrants and 71 potential aliases in the Alphabay-Dreams-Silk dataset, (ii) 17 migrants and 3 potential aliases in the Valhalla-Berlusconi dataset, and (iii) 75 migrants and 10 potential aliases in the Traderoute-Agora dataset.Altogether, our approach can help Law Enforcement Agencies (LEA) make more informed decisions by verifying and identifying migrating vendors and their potential aliases on existing and Low-Resource (LR) emerging Darknet markets.

Statutory article retrieval (SAR), the task of retrieving statute law articles relevant to a legal question, is a promising application of legal text processing. In particular, high-quality SAR systems can improve the work efficiency of legal professionals and provide basic legal assistance to citizens in need at no cost. Unlike traditional ad-hoc information retrieval, where each document is considered a complete source of information, SAR deals with texts whose full sense depends on complementary information from the topological organization of statute law. While existing works ignore these domain-specific dependencies, we propose a novel graph-augmented dense statute retriever (G-DSR) model that incorporates the structure of legislation via a graph neural network to improve dense retrieval performance. Experimental results show that our approach outperforms strong retrieval baselines on a real-world expert-annotated SAR dataset.

Human trafficking (HT) is a pervasive global issue affecting vulnerable individuals, violating their fundamental human rights. Investigations reveal that many HT cases are associated with online advertisements (ads), particularly in escort markets. Consequently, identifying and connecting HT vendors has become increasingly challenging for Law Enforcement Agencies (LEAs). To address this issue, we introduce IDTraffickers, an extensive dataset consisting of 87,595 text ads and 5,244 vendor labels to enable the verification and identification of potential HT vendors on online escort markets. To establish a benchmark for authorship identification, we train a DeCLUTR-small model, achieving a macro-F1 score of 0.8656 in a closed-set classification environment. Next, we leverage the style representations extracted from the trained classifier to conduct authorship verification, resulting in a mean r-precision score of 0.8852 in an open-set ranking environment. Finally, to encourage further research and ensure responsible data sharing, we plan to release IDTraffickers for the authorship attribution task to researchers under specific conditions, considering the sensitive nature of the data. We believe that the availability of our dataset and benchmarks will empower future researchers to utilize our findings, thereby facilitating the effective linkage of escort ads and the development of more robust approaches for identifying HT indicators (1).

Courts commonly rely on precedents to guide their judgments. Centrality measures have been used to calculate precedence value in citation networks of judgments, yet it remains largely unknown whether and which centrality measures correlate well to precedent value. An analysis of European Court of Human Rights (ECtHR) judgments offers a unique opportunity to uncover this relationship, as the ECtHR publishes an importance score for its judgments and the branch of court that dealt with them. These scores, although not perfect, may serve as proxies for a case’s precedent value. Various network centrality measures correlated reasonably with these proxies, with Degree being a stable measure across the (sub)networks. An ordinal regression model with network centrality among other predictor variables performed reasonably when Importance Score was used as an outcome variable (F1 ≈ .655). The results support that network centrality, to an extent, indicates case precedent value, and that Degree seems to be a stable proxy for precedent value across different networks. The data, code, and additional results are made available.

A challenge in computational legal research is the quantitative assessment of “relevance” in a network of court decisions. The term “sleeping beauty” (SB) was coined to denote an article that received almost no attention immediately after publication, but suddenly received multiple citations many years later. These publications can be identified by calculating their Beauty coefficient (B-coefficient). In this contribution, we apply approaches used for identifying SBs to decisions arising from the Court of Justice of the European Union (CJEU). We compared B-coefficients of CJEU cases with their centrality scores from classical algorithms from network analysis, finding that these measures tend to correlate. We discuss the implications of this that are interesting for legal scholars, acknowledging that future work is required to calibrate the scale of the time variable in the B-coefficient formula for finer-grained application to case law. Our study’s setup provides a foundation for new case law analytics methodologies that extends the power of traditional network analysis techniques for answering questions about the behavior of European courts.

Identification of relevant or similar court decisions is a core activity in legal decision making for case law researchers and practitioners. With an ever increasing body of case law, a manual analysis of court decisions can become practically impossible. As a result, some decisions are inevitably overlooked. Alternatively, network analysis may be applied to detect relevant precedents and landmark cases. Previous research suggests that citation networks of court decisions frequently provide relevant precedents and landmark cases. The advent of text similarity measures (both syntactic and semantic) has meant that potentially relevant cases can be identified without the need to manually read them. However, how close do these measures come to approximating the notion of relevance captured in the citation network? In this contribution, we explore this question by measuring the level of agreement of state-of-the-art text similarity algorithms with the citation behavior in the case citation network. For this paper, we focus on judgements by the Court of Justice of the European Union (CJEU) as published in the EUR-Lex database. Our results show that similarity of the full texts of CJEU court decisions does not closely mirror citation behaviour, there is a substantial overlap. In particular, we found syntactic measures surprisingly outperform semantic ones in approximating the citation network.

The availability of large collections of digitalized legal texts raises an opportunity for new methodologies in legal scholarship. Analysis of citation networks of case law gives insight into which cases are related and to determine their relevance. Software tools that provide an graphical interface to case law networks are required in order to enable non-technical researches to use network analysis methodologies. In this study, we present open source software for the analysis and visualization of networks of Dutch case law, aimed for use by legal scholars. This technology assists in answering legal research questions, including determining relevant precedents, comparing the precedents with those identified in the literature, and determining clusters of related cases. The technology was used to analyze a network of cases related to employer liability.