This model is part of the Mecellem project, presented in the paper Mecellem Models: Turkish Models Trained from Scratch and Continually Pre-trained for the Legal Domain. Muhakim (ArmoRM-Turkish-Legal) is a domain-specific multi-objective reward model trained for Turkish legal text assessment. Built upon the Skywork-Reward-V2-Llama-3.1-8B backbone (8B parameters) and augmented with a mixture-of-experts gating mechanism, the model produces fine-grained quality scores across five legally grounded dimensions. The training pipeline consists of three components: (i) multi-objective supervision that enables independent learning of five legal quality dimensions, (ii) preference-based training of a mixture-of-experts gating network to capture context-dependent importance of these dimensions, and (iii) a debiasing stage designed to mitigate length-related reward artifacts. Key Features: — Multi-objective reward model with five legal quality dimensions — Context-aware evaluation through mixture-of-experts gating mechanism — Trained for benchmarking decoder-only language models in Turkish legal tasks — Evaluates quality across: statute reference, legal accuracy, case law reference, linguistic…
Модальности:
Генерация текста
Области применения:
Диалог / чат Юриспруденция
Задача: Генерация текста
Автор: newmindai
Теги: armorm, text-classification, reward-model, turkish, legal, turkish-legal, mecellem, armo
Лайков: 4 | Загрузок: 7
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
