AUEB-Archimedes at RIRAG-2025: Is Obligation concatenation really all you need?

Ioannis Chasandras, Odysseas S. Chlapanis, Ion Androutsopoulos


Abstract
This paper presents the systems we developed for RIRAG-2025, a shared task that requires answering regulatory questions by retrieving relevant passages. The generated answers are evaluated using RePASs, a reference-free and model-based metric. Our systems use a combination of three retrieval models and a reranker. We show that by exploiting a neural component of RePASs that extracts important sentences (‘obligations’) from the retrieved passages, we achieve a dubiously high score (0.947), even though the answers are directly extracted from the retrieved passages and are not actually generated answers. We then show that by selecting the answer with the best RePASs among a few generated alternatives and then iteratively refining this answer by reducing contradictions and covering more obligations, we can generate readable, coherent answers that achieve a more plausible and relatively high score (0.639).
Anthology ID:
2025.regnlp-1.8
Volume:
Proceedings of the 1st Regulatory NLP Workshop (RegNLP 2025)
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Tuba Gokhan, Kexin Wang, Iryna Gurevych, Ted Briscoe
Venues:
RegNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
52–58
Language:
URL:
https://aclanthology.org/2025.regnlp-1.8/
DOI:
Bibkey:
Cite (ACL):
Ioannis Chasandras, Odysseas S. Chlapanis, and Ion Androutsopoulos. 2025. AUEB-Archimedes at RIRAG-2025: Is Obligation concatenation really all you need?. In Proceedings of the 1st Regulatory NLP Workshop (RegNLP 2025), pages 52–58, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
AUEB-Archimedes at RIRAG-2025: Is Obligation concatenation really all you need? (Chasandras et al., RegNLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.regnlp-1.8.pdf