Metraipolis › archive › dc_24dffddc1036
Tool-calling retrieval versus vector RAG for a small Greek--English knowledge base: accuracy and robustness to how users type Greek — arXiv:2610.08205
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.08205
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:21:34.535Z
- SHA-256 of the archived text
c689ba03944c2a33e6c3c594f094fbee490ce138274d77327e09f1690c9732f8- Stable URL of this page
https://metraipolis.com/documento/dc_24dffddc1036
How to cite
Tool-calling retrieval versus vector RAG for a small Greek--English knowledge base: accuracy and robustness to how users type Greek — arXiv:2610.08205 — arXiv (en), https://arxiv.org/abs/2610.08205 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_24dffddc1036 (Metraipolis archive dc_24dffddc1036, sha256 c689ba03944c2a33e6c3c594f094fbee490ce138274d77327e09f1690c9732f8)
BibTeX
@misc{dc24dffddc1036,
title = {Tool-calling retrieval versus vector RAG for a small Greek--English knowledge base: accuracy and robustness to how users type Greek — arXiv:2610.08205},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.08205},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_24dffddc1036; sha256 c689ba03944c2a33e6c3c594f094fbee490ce138274d77327e09f1690c9732f8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08205. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Assistants grounded in a small, frequently edited knowledge base can retrieve through tool calls to a live data interface or through vector retrieval-augmented generation (RAG). We compare the two on KyGround, a benchmark of 198 questions drawn from the published records of a Greek--English agricultural platform on Kythera, Greece, with answers verified automatically against the records and each question posed in up to nine forms, including Greek without accents, in capitals and in three Latin-script (Greeklish) schemes. With Claude Haiku 4.5 as router and answer model, a reconstruction of the platform's tool agent answered 71.6\% of canonical Greek questions correctly and vector RAG 95.3\% (difference $-23.6$ percentage points, 95\% CI $-33.1$ to $-15.1$). Letting the router write the vector query changed nothing, and placing the whole knowledge base of about 26,000 tokens in the prompt reached 99.3\%. The tool agent's losses arose in retrieval. Its literal searches returned nothing when the router's arguments did not occur verbatim in a record, for example when it transliterated Greek into Latin script or combined words that occur in a record but not as one phrase, and the agent then abstained. Unaccented and capitalised questions cost the tool agent about 20 points and vector RAG at most 2; accent-insensitive search removed this loss, and matching stemmed tokens raised the tool agent to 83.8\% on canonical Greek. Greeklish cost both designs about 21 to 32 points. Tool interfaces for community knowledge bases need search that tolerates how users type. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computational Engineering, Finance, and Science (cs.CE) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.08205 — 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 2026-10-07T11:15:24.806Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).