Nouvelles.droit.org

🕒
RSS JSON
act small models ministers summarization scottish sum procedure landlord their legislative parliamentary normative slms local performance evaluation tribunal documents language housing llms holder property var texts chamber regulations scotland information sections
2 Résultats (1 - 2)
The First-tier Tribunal for Scotland Housing and Property Chamber (Procedure) Amendment Regulations 2026 (UK Legilsation News)
: These Regulations amend the First-tier Tribunal for Scotland Housing and Property Chamber (Procedure) Regulations 2017 (S.S.I. 2017/328) (“the principal Regulations”) to reflect the conferral of new functions on the First-tier Tribunal by sections 16 and 17 of the Housing (Scotland) Act 2025 (asp 13) (“the 2025 Act”). Section 14 of the 2025 Act gives local authorities and the Scottish Ministers powers to seek information from a landlord relating to the tenancy of a house included in the landlord’s entry in the landlord register. These Regulations make provision for an application to be made to the First-tier Tribunal by a local authority or the Scottish Ministers where an information holder fails to provide information without reasonable excuse, or provides information that the information holder must have known to be false in a material
Small Language Models for Legislative Summarization: An Empirical Evaluation of Performance and Suitability (Scoop.it - Documentation juridique (Stéphan Cottin))
: Parliamentary institutions generate extensive, domain-specific legislative documents, including normative texts and parliamentary debate transcripts. These documents differ in content and linguistic complexity, making automatic summarization essential for producing coherent summaries aligned with institutional standards. While large language models (LLMs) achieve high summarization quality, their computational requirements limit deployment in parliamentary and public-sector environments. In contrast, small language models (SLMs) offer a more resource-efficient alternative, but their capabilities and performance relative to LLMs, extractive methods, and other SLMs remain underexplored. In this work, we present the first comprehensive evaluation of SLMs for legislative summarization, assessing their effectiveness across document types and languages. We use two complementary datasets: EUR-Lex-Sum, a multilingual corpus of normative texts covering six European languages, and ParcanDeb-Sum, a Spanish dataset of p[...]