AI4EVIR
Workshop AI4EVIR: AI for Evidential Reasoning
Updated Schedule!
Tuesday December 9th, morning session (09:00-13:00), at Cavallerizza Reale – Piazza Vittorio Veneto, Sala Multifunzione.
09:00-09:15 Opening
09:15-09:50
Invited talk: Marouschka Vink
09:50-10:30 Session 1
09:50 - 10:10 - Federico Costantini, Fausto Galvan, Francesco Crisci, Luca Baron and Pier Luca Montessoro - The Quality Assessment of LLM in Digital Forensics
10:10 - 10:30 - Anne Ruth Mackor and Henry Prakken - On Reporting Likelihood Ratios of Exhaustive and Non-Exhaustive Hypotheses about Rare Events in Criminal Cases
10:30 - 11:00 Coffee break
11:00 - 12:40 Session 2
11:00 - 11:10 - Shawn Bowers and Bertram Ludäscher - Towards Trustworthy AI Results using Evidence Structures: From Certificates to Argumentation Frameworks
11:10 - 11: 30 Leya Hampson and Ludi van Leeuwen - Investigating the value of qualitative Bayesian networks of complete cases as “double-check” tools on traditional judicial reasoning: An exploratory study
11:30 - 11:50 - Aybüke Özgün and Daira Pinto Prieto - A Qualitative Logic for Uncertain Evidence and Belief Comparison
11:50 - 12:10 - Mengxuan Helen Qiao, Vanessa Cheung, Leya Hampson and David Lagnado - Recency Effects, Cautious Convictions, and Conservative Updating in GPT-4o’s Legal Decisions
12:10 - 12:30 - Henrik Palmer Olsen, Mohammad N S Jahromi, Frederik Bay-Jørgensen, Thomas B Moeslund and Thomas Gammeltoft-Hansen - Managing Fuzziness: Leveraging LLMs for Discovering Credibility Indicators in Asylum Cases
12:30 - 13:00 - Wrapup Discussion and closing
Call for Papers
(in conjunction with JURIX 2025, 10–11 December, Turin)
Workshop date: 9 December 2025
Reasoning with evidence to establish relevant facts lies at the heart of legal reasoning. Technologies that allow us to reason about facts are evolving, and new kinds of evidence are becoming available (for example, digital forensic science). At the same time, reasoning with evidence is a dynamic and complex process: practitioners must decide what evidence to collect and how to interpret it amid vast amounts of data. These choices in selecting evidence and the following reasoning with evidence are complex tasks that may benefit from standardization and assistance by AI, for example, to avoid probabilistic and other fallacies.
The AI for Evidential Reasoning workshop aims to bring together researchers working on formal, computational, and empirical approaches to reasoning with evidence, as well as those with expertise in forensic science and evidence evaluation. The goal is to foster discussion and exchange between theoretical and applied perspectives on how AI can contribute to evidential reasoning in legal and investigative contexts.
The half-day workshop will feature:
- A keynote “the evaluation of digital findings in forensic casework” by Marouschka Vink from the Netherlands Forensic Institute (NFI)
- Paper presentations on accepted papers
- A discussion session focused on practical examples
The workshop proceedings will be submitted to CEUR for publication.
Topics of interest
We invite contributions on topics including (but not limited to):
- Formal models of evidential reasoning (scenarios, arguments, probabilities)
- Hypothesis generation, falsification, and verification
- Methods such as Bayesian Networks, Chain Event Graphs, scenario-based reasoning, formal argumentation, Hypothesis Management Frameworks, etc.
- Legal and commonsense reasoning with evidence
- Empirical studies and data-driven analyses of reasoning with evidence
- Case studies on real or hypothetical cases
- Practical argumentation
- Large language models (LLMs) and reasoning with evidence
- Agentic and multi-agent approaches
- Philosophical perspectives on the nature and role of evidence
Program Committee
Burkhard Schafer
Florix Bex
Rineke Verbrugge
Anne Ruth Mackor
William Thompson
Hylke Jellema
Amy Wilson
Giovanni Tuzet
Henry Prakken
Daphne Odekerken
David Lagnado
Annet Onnes
Cor Steging
Marouschka Vink
Silja Renooij
Marcello Di Bello
Jeroen Keppens
Christian Dahlman
Organizers
Ludi van Leeuwen - Rijksuniversiteit Groningen (l.s.van.leeuwen@rug.nl)
Roos Scheffers - Utrecht Universiteit (r.j.scheffers@uu.nl)
Bart Verheij - Rijksuniversiteit Groningen
Submission guidelines
We welcome:
- Regular papers (up to 12 pages, excluding references) presenting completed research
- Short papers (up to 6 pages, excluding references) describing work in progress, demos, visions, and ideas
Submissions must follow the CEUR-WS template (Download LaTeX paper template) and be submitted via EasyChair.
Important dates (AoE)
Submission deadline: 10 November
Notification of acceptance: 24 November
Camera-ready version: 7 December
Schedule & Location
EasyChair: https://easychair.org/my/conference?conf=ai4evir
Conference website: https://jurix2025.di.unito.it/home