Optimizing Efficiency in Multi-Stage Semantic Re-ranking Architectures

Artur M. A. Novais, Anna P. V. L. B. Moreira, Maria C. X. de Almeida, João P. C. Presa, Fernando M. Federson, Sávio S. T. de Oliveira


Abstract
Semantic re-ranking architectures based on cross-encoders are essential for high-precision Information Retrieval (IR) in the legal domain, but they face a dilemma: their high computational latency renders large-scale applications challenging, particularly in resource-constrained environments. Traditional single-stage approaches force a choice between computational efficiency and ranking quality. This work presents an empirical evaluation of established cascade re-ranking architectures to optimize this balance through the adaptive application of off-the-shelf models of increasing complexity over progressively smaller sets of candidates. We validated the architecture on a corpus of 300,000 legal documents in Portuguese from the Court of Accounts of the State of Goiás (TCE-GO). Experiments demonstrate a 60.3% reduction in latency (from 11.75s to 4.66s per query) compared to the most precise single-stage baseline, with a marginal degradation of only 2 p.p. in R@avg and 0.0224 in MRR@avg. The results validate the semantic funnel as a computationally viable solution for semantic document-to-document search within the specific context of the TCE-GO repository, establishing a baseline for future transferability studies in broader Portuguese legal contexts.
Anthology ID:
2026.propor-1.55
Volume:
Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1
Month:
April
Year:
2026
Address:
Salvador, Brazil
Editors:
Marlo Souza, Iria de-Dios-Flores, Diana Santos, Larissa Freitas, Jackson Wilke da Cruz Souza, Eugénio Ribeiro
Venue:
PROPOR
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
562–571
Language:
URL:
https://aclanthology.org/2026.propor-1.55/
DOI:
Bibkey:
Cite (ACL):
Artur M. A. Novais, Anna P. V. L. B. Moreira, Maria C. X. de Almeida, João P. C. Presa, Fernando M. Federson, and Sávio S. T. de Oliveira. 2026. Optimizing Efficiency in Multi-Stage Semantic Re-ranking Architectures. In Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1, pages 562–571, Salvador, Brazil. Association for Computational Linguistics.
Cite (Informal):
Optimizing Efficiency in Multi-Stage Semantic Re-ranking Architectures (Novais et al., PROPOR 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.propor-1.55.pdf