Metraipolis › archive › dc_db6d30b8b376

ReX-GG: a LLM Ensemble Pipeline for Relation-extraction and Graph Generation — arXiv:2610.41901

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41901
License (as archived)
CC0-1.0
Archived
2026-11-02T06:59:23.414Z
SHA-256 of the archived text
b0f4a2731b4dec8374942decaeace361e1e5de423a7cace1c4a9d7eade11c85c
Stable URL of this page
https://metraipolis.com/documento/dc_db6d30b8b376

How to cite

ReX-GG: a LLM Ensemble Pipeline for Relation-extraction and Graph Generation — arXiv:2610.41901 — arXiv (en), https://arxiv.org/abs/2610.41901 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db6d30b8b376 (Metraipolis archive dc_db6d30b8b376, sha256 b0f4a2731b4dec8374942decaeace361e1e5de423a7cace1c4a9d7eade11c85c)
BibTeX
@misc{dcdb6d30b8b376,
  title = {ReX-GG: a LLM Ensemble Pipeline for Relation-extraction and Graph Generation — arXiv:2610.41901},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41901},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db6d30b8b376; sha256 b0f4a2731b4dec8374942decaeace361e1e5de423a7cace1c4a9d7eade11c85c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41901. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Current LLM ensemble frameworks focus on multi-step setups with additional modules for answer ranking, often opting for token and span analysis rather than structured outputs, leading to heavyweight architectures with potential fail states along the pipeline. Faster, lighter solutions are more vulnerable to hallucination propagation and can lack output control in more complex pipelines. This paper proposes a customisable, lightweight ensemble workflow of coordinated Large Language Models that leverages JSON-structured outputs and anonymous peer-review ranking to mitigate hallucinatory outputs and single-model failure points. The pipeline is demonstrated on a relation extraction task applied to popular science articles in English, targeting four ontologically-grounded relation types (strong causation, weak causation, contrastive, and compositional), with semantic node canonicalisation and interactive, colour-coded HTML causal graphs as the final output. Performance is evaluated through an anonymous user study, achieving an average perceived accuracy of 0.778 against a human-annotated gold standard. The modular architecture supports flexible deployment across both API-based and in-house LLM setups, and the full framework is released under an open license to foster reproducibility and collaborative research.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.41901 — 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 2026-11-02T06:56:58.324Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).