Metraipolis › archive › dc_7752caa18630

GreekBarRetrieval: A Benchmark for Greek Statutory Retrieval — arXiv:2608.18752

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18752
License (as archived)
CC0-1.0
Archived
2026-10-18T14:03:41.974Z
SHA-256 of the archived text
0116c392a7deb37ce48ae6fcbd36edf915a1bf4b6ad8111919b5df9cf49522af
Stable URL of this page
https://metraipolis.com/documento/dc_7752caa18630

How to cite

GreekBarRetrieval: A Benchmark for Greek Statutory Retrieval — arXiv:2608.18752 — arXiv (en), https://arxiv.org/abs/2608.18752 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7752caa18630 (Metraipolis archive dc_7752caa18630, sha256 0116c392a7deb37ce48ae6fcbd36edf915a1bf4b6ad8111919b5df9cf49522af)
BibTeX
@misc{dc7752caa18630,
  title = {GreekBarRetrieval: A Benchmark for Greek Statutory Retrieval — arXiv:2608.18752},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18752},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7752caa18630; sha256 0116c392a7deb37ce48ae6fcbd36edf915a1bf4b6ad8111919b5df9cf49522af},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18752. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Statutory retrieval is necessary for citation-grounded legal question answering, but remains underexplored for Greek. We introduce GreekBarRetrieval, a public retrieval benchmark derived from, and complementing GreekBarBench, which did not include retrieval. The new benchmark comprises 283 bar-exam questions, each accompanied by the facts of the case it refers to, and 6,308 candidate statutory articles to retrieve from. Questions and facts are stated in everyday language, but need to be mapped to the formal terminology of statutes and their abstract legal concepts. A further complication is that not all of the case facts are relevant to each question of a case. Experimenting with three BM25 variants and nine dense retrievers, we find that vanilla dense retrieval far outperforms vanilla sparse retrieval in Recall@100. However, LLM-based query reformulation helps BM25 close that gap, while also improving dense retrieval. With a ten-round ReAct-like LLM reformulation loop that we introduce, BM25 improves further in Recall@100 and obtains the best nDCG and MAP scores of all tested retrievers. Query reformulation also outperforms pseudo-relevance feedback, sparse-dense fusion, and English translation.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-20 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.18752 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T13:59:46.169Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).