AI ethics evidence index Search
Source-linked daily record
Evidence record 18662 · automatically gathered

Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation

We study reference-free post-training for multilingual machine translation with open large language models. Starting from the supervised-finetuned MiLMMT-46-v0.1 models, we apply Group Relative Policy Optimization (GRPO) with a reward that averages two reference-free quality estimation models and is gated by language identification. We then linearly interpolate the supervised fine-tuning (SFT) and reinforcement learning (RL) model checkpoints to obtain MiLMMT-46-v1.0. Across 46 languages, the re

Record details

Published: 11 August 2026
Source: arXiv cs.AI
Category: Research
Topics: Regulation
Retrieved: 12 August 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Same publisher byline · Shared topic: Regulation

Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation

HuggingFace Daily Papers · 10 August 2026

Shared topic: Regulation

A Gateway Architecture for Enterprise MCP Authentication: Unifying Heterogeneous Auth, Identity Delegation, and the User / Non-User Persona Problem

arXiv · 11 August 2026

Shared topic: Regulation

SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense

arXiv red teaming query · 11 August 2026

Shared topic: Regulation

Longitudinal Evidence That General-Purpose Chatbots Actively Foster Relational Engagement

arXiv · 11 August 2026

Shared topic: Regulation

IADD-TR: Intervention-Aware Dynamics Decoupling with Targeted Regularization for Model-Based Reinforcement Learning

arXiv cs.LG · 11 August 2026

Shared topic: Regulation

Putting Registers to Work: Task Registers for Token Pruning in Vision Transformers

arXiv cs.AI · 11 August 2026

How to cite this record

ethics.ai (11 August 2026), “Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation,” evidence record 18662, https://ethics.ai/record/18662 (originally published by arXiv cs.AI).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.