Publications
Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challenges
This research provides an overview of NLP tasks specific to legal text, such as Document Summarisation, Named Entity Recognition, Question Answering, Argument Mining, Text Classification, and Judgement Prediction.
Authors: Farid Ariai, Joel Mackenzie, and Gianluca Demartini
Published in: ACM Computing Surveys
, Nov 2025
Adaptive political surveys and GPT-4: Tackling the cold start problem with simulated user interactions
This research compares the distribution of LLM-generated data to real candidates' responses in a political questionnaire and evaluates the synthetic data’s useful to train statistical models.
Authors: Fynn Bachmann, Daan Van Der Weijden, Lucien Heitz, Cristina Sarasua, and Abraham Bernstein
Published in: PLoS One
, May 2025
Fast and Adaptive Questionnaires for Voting Advice Applications
This research introduces an adaptive questionnaire for Voting Advice Applications that enhances recommendation accuracy from 40% to 74% by dynamically selecting questions based on users’ previous answers.
Authors: Fynn Bachmann, Cristina Sarasua, and Abraham Bernstein
Published in: Proceedings of the European Conference for Machine Learning (ECML)
, Jun 2024