Structured Document Translation via Format Reinforcement Learning

Haiyue Song, Johannes Eschbach-Dymanus, Hour Kaing, Sumire Honda, Hideki Tanaka, Bianka Buschbeck, Masao Utiyama

Structured Document Translation via Format Reinforcement Learning: 2 upvotes on Hugging Face Daily Papers, #28 of 32 papers on 2025-12-09. Day-by-day upvote history.

Recent works on structured text translation remain limited to the sentence level, as they struggle to effectively handle the complex document-level XML or HTML structures. To address this, we propose Format Reinforcement Learning (FormatRL), which employs Group Relative Policy Optimization on top of a supervised fine-tuning model to directly optimize novel structure-aware rewards: 1) TreeSim, which measures structural similarity between predicted and reference XML trees and 2) Node-chrF, which measures translation quality at the level of XML nodes. Additionally, we apply StrucAUC, a fine-grained metric distinguishing between minor errors and major structural failures. Experiments on the SAP software-documentation benchmark demonstrate improvements across six metrics and an analysis further shows how different reward functions contribute to improvements in both structural and translation quality.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.