Mattia Falduti | Searcharxiv

arXiv2026

An AI-Based Approach to Early Reporting and Justice Initiation in Image-based Sexual Abuse. A Pilot Study

Against the background of the widespread use of Artificial Intelligence (AI) tools in the field of justice, this paper aims to explore how an AI solution designed to draft initial reports for reporting image-based sexual abuses (IBSA) could help, support, or assist in facilitating access to justice. In our approach, access to justice is facilitated not only by easing the path to denounce IBSA (which currently has the lowest reporting rate), but also by offering an early, and thus more accurate, report draft to law enforcement authorities, providing later support also for judges. Building upon earlier approaches, we designed an improved version and tested it with three experts. In this sense, the paper advocates for AI solutions offering effective and efficient support in early reporting of IBSA.

cs.CY↗

arXiv2021

Lex Rosetta: Transfer of Predictive Models Across Languages, Jurisdictions, and Legal Domains

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

cs.CL↗