AUEB-Archimedes at RIRAG-2025: Is obligation concatenation really all you need?
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929632859652096 |
|---|---|
| author | Chasandras, Ioannis Chlapanis, Odysseas S. Androutsopoulos, Ion |
| author_facet | Chasandras, Ioannis Chlapanis, Odysseas S. Androutsopoulos, Ion |
| contents | 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). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_11567 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AUEB-Archimedes at RIRAG-2025: Is obligation concatenation really all you need? Chasandras, Ioannis Chlapanis, Odysseas S. Androutsopoulos, Ion Computation and Language 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). |
| title | AUEB-Archimedes at RIRAG-2025: Is obligation concatenation really all you need? |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2412.11567 |