Metraipolis › archive › dc_c3cd2e26abcf
Retrieval-Augmented Multi-Prompt Ensemble for Minor-Grain Breeding Information Extraction — arXiv:2609.07134
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.07134
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T12:45:27.564Z
- SHA-256 of the archived text
85101b0e1b6c98c5c7e16030c713b29d57336cdd697de2c0c7dc15c99407172c- Stable URL of this page
https://metraipolis.com/documento/dc_c3cd2e26abcf
How to cite
Retrieval-Augmented Multi-Prompt Ensemble for Minor-Grain Breeding Information Extraction — arXiv:2609.07134 — arXiv (en), https://arxiv.org/abs/2609.07134 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c3cd2e26abcf (Metraipolis archive dc_c3cd2e26abcf, sha256 85101b0e1b6c98c5c7e16030c713b29d57336cdd697de2c0c7dc15c99407172c)
BibTeX
@misc{dcc3cd2e26abcf,
title = {Retrieval-Augmented Multi-Prompt Ensemble for Minor-Grain Breeding Information Extraction — arXiv:2609.07134},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.07134},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c3cd2e26abcf; sha256 85101b0e1b6c98c5c7e16030c713b29d57336cdd697de2c0c7dc15c99407172c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07134. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper presents our system for CCL2026-Eval Task 5: Minor-Grain Breeding Information Extraction (MGBIE), which jointly extracts 12 entity types and 6 relation types from minor-grain breeding literature. We propose RAME (Retrieval-Augmented Multi-Prompt Ensemble), a training-free framework that elicits multiple LLM outputs under controlled diversity and aggregates them by majority voting to obtain high-confidence predictions. RAME combines (i) retrieval-augmented few-shot selection via a hybrid BM25-embedding retriever, (ii) a three-prompt ensemble (Strict, Relaxed, Balanced) spanning the precision to recall spectrum, and (iii) large-scale repeated sampling with majority voting to filter noisy predictions. Built on DeepSeek-V4-Flash, RAME achieves a Total Score of 0.499 (NER 0.730, RE 0.346) on the leaderboard, ranking 1st and surpassing the official Track-A baseline powered by GPT-5.5 (0.448), representing an 11.4% relative improvement. Code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.07134 — 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 2026-10-16T12:30:25.095Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).