Introduces NormBench benchmark and Span-Grounded Deontic Trees (SG-DT) for defeasible scope parsing to reduce Silent Scope Omission in LLMs on statutes and policies.
arXiv preprint arXiv:2509.14507 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
YouZhi-LLM applies a layer-adaptive GQA-to-MLA transition plus Ascend-specific distillation and fine-tuning to reduce KV-cache size, yielding up to 2.69× higher concurrency and modest gains on financial benchmarks versus base models.
citing papers explorer
-
From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing
Introduces NormBench benchmark and Span-Grounded Deontic Trees (SG-DT) for defeasible scope parsing to reduce Silent Scope Omission in LLMs on statutes and policies.
-
YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition
YouZhi-LLM applies a layer-adaptive GQA-to-MLA transition plus Ascend-specific distillation and fine-tuning to reduce KV-cache size, yielding up to 2.69× higher concurrency and modest gains on financial benchmarks versus base models.