ReX-GG: A LLM Ensemble Pipeline for Relation-extraction and Graph Generation

Giacomo Magnifico, Eduard Barbu


Abstract
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 English popular science articles, 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.
Anthology ID:
2026.kallm-1.10
Volume:
Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Gilles Sérasset, Katerina Gkirtzou, Michael Cochez, Jan-Christoph Kalo
Venues:
KaLLM | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
93–101
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-kgllm-10
DOI:
10.63317/2qkh8idwebsv
Bibkey:
Cite (ACL):
Giacomo Magnifico and Eduard Barbu. 2026. ReX-GG: A LLM Ensemble Pipeline for Relation-extraction and Graph Generation. In Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26, pages 93–101, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
ReX-GG: A LLM Ensemble Pipeline for Relation-extraction and Graph Generation (Magnifico & Barbu, KaLLM 2026)
Copy Citation: