Tuan-Quang Vuong — accepted AI-conference papers

2025

LexTempus: Enhancing Temporal Generalizability of Legal Language Models Through Dynamic Mixture of Experts

ACL 2025long

The rapid evolution of legal concepts over time necessitates that legal language models adapt swiftly accounting for the temporal dynamics. However, prior works have largely neglected this crucial dimension, treating legal adaptation as a static problem rather than a continuous process. To address t…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

ChronosLex: Time-aware Incremental Training for Temporal Generalization of Legal Classification Tasks

Santosh T.y.s.s, Tuan-Quang Vuong, Matthias Grabmair

ACL 2024long

This study investigates the challenges posed by the dynamic nature of legal multi-label text classification tasks, where legal concepts evolve over time. Existing models often overlook the temporal dimension in their training process, leading to suboptimal performance of those models over time, as t…

Cited by 4 Source ↗PDF ↗Scholar ↗