Metraipolis › archive › dc_c03213ff4c5a
Cascading Circle Loss: Order-Preserving Contrastive Learning for Graded Legal Retrieval — arXiv:2611.10765
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.10765
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:44:30.275Z
- SHA-256 of the archived text
37fb7cc6e679573f5333a62ef20f8dd1dc1cf8b68891b587c61e3e5f7d5d56ef- Stable URL of this page
https://metraipolis.com/documento/dc_c03213ff4c5a
How to cite
Cascading Circle Loss: Order-Preserving Contrastive Learning for Graded Legal Retrieval — arXiv:2611.10765 — arXiv (en), https://arxiv.org/abs/2611.10765 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c03213ff4c5a (Metraipolis archive dc_c03213ff4c5a, sha256 37fb7cc6e679573f5333a62ef20f8dd1dc1cf8b68891b587c61e3e5f7d5d56ef)
BibTeX
@misc{dcc03213ff4c5a,
title = {Cascading Circle Loss: Order-Preserving Contrastive Learning for Graded Legal Retrieval — arXiv:2611.10765},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.10765},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c03213ff4c5a; sha256 37fb7cc6e679573f5333a62ef20f8dd1dc1cf8b68891b587c61e3e5f7d5d56ef},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10765. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper introduces Cascading Circle Loss (CasCL), a contrastive learning framework for legal retrieval tasks with graded relevance. CasCL combines an InfoNCE objective for positive-negative separation with a cascade of ranking boundaries that model ordered relevance levels between queries and legal clauses. The framework also includes a negative-aware self-paced optimization mechanism and a relevance gain weighting strategy to improve ranking quality. Experiments on legal passage retrieval benchmarks show that CasCL consistently outperforms existing methods, including InfoNCE, Circle Loss, MNRL and Margin MSE, across both binary retrieval and graded ranking metrics. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2611.10765 — 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 2026-11-10T18:37:52.428Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).