- Source
- arXiv
- Published
- 15 Jan 2026
- Authors
- David Samuel Setiawan, Raphaël Merx, Jey Han Lau
Excerpt from source
Neural Machine Translation (NMT) models for low-resource languages suffer significant performance degradation under domain shift. We quantify this challenge using Dhao, an indigenous language of Eastern Indonesia with no digital footprint beyond the New Testament (NT). When applied to the unseen Old Testament (OT), a standard NMT model fine-tuned on the NT drops from an in-domain score of 36.17 chrF++ to 27.11 chrF++. To recover this loss, we introduce a hybrid framework where a fine-tuned NMT model generates an initial draft, which is then refined by a Large Language Model (LLM) using…
These stories are gathered automatically from across the web and each source link is checked. A summary never replaces the original — always read the source. Inclusion here is not endorsement.