# Blog · Aitranslations

> Aitranslations — Recent headlines.

- [Glossary Drift in Low-Resource NMT: Fixes, Mistakes, Tactics](https://aitranslations.io/blog/glossary-drift-in-low-resource-nmt-fixes-mistakes-tactics.php/index.md)
- [Why Nyanja Rankings Invert on FLORES-200: Metrics Explained](https://aitranslations.io/blog/why-nyanja-rankings-invert-on-flores-200-metrics-explained.php/index.md)
- [The Agglutination Tax: How Neural MT Benchmarks Fail Turkish](https://aitranslations.io/blog/the-agglutination-tax-how-neural-mt-benchmarks-fail-turkish.php/index.md)
- [JRC 2026: Legal NMT Entropy Drift & 38% Unconstrained LLM Penalty](https://aitranslations.io/blog/jrc-2026-legal-nmt-entropy-drift-38-unconstrained-llm-penalty.php/index.md)
- [CometKiwi 0.85 Gate: Threshold Math, 0.80 vs 0.85 vs 0.90](https://aitranslations.io/blog/cometkiwi-085-gate-threshold-math-080-vs-085-vs-090.php/index.md)
- [Beam Search vs Sampled Decoding: Why Language Isn't the Switch](https://aitranslations.io/blog/beam-search-vs-sampled-decoding-why-language-isnt-the-switch.php/index.md)
- [Inside WMT24's Three Scorers: COMET-22 and the Coverage Gap](https://aitranslations.io/blog/inside-wmt24s-three-scorers-comet-22-and-the-coverage-gap.php/index.md)
- [Article 53 Bans BLEU, Mandates COMET-QA & Explainable Metrics](https://aitranslations.io/blog/article-53-bans-bleu-mandates-comet-qa-explainable-metrics.php/index.md)
- [Legal MT Fine-Tuning: Why 27% Drift Reduction Masks Critical Gaps](https://aitranslations.io/blog/legal-mt-fine-tuning-why-27-drift-reduction-masks-critical-gaps.php/index.md)
- [LangGraph NMT Latency & Token Cost: 2026 Pricing Tactics](https://aitranslations.io/blog/langgraph-nmt-latency-token-cost-2026-pricing-tactics.php/index.md)
- [Legal NMT Term Drift: Causes, Fixes & 2026 WMT Insights](https://aitranslations.io/blog/legal-nmt-term-drift-causes-fixes-2026-wmt-insights.php/index.md)
- [chrF vs BLEU: WMT23 Legal Task Proves They Really Differ](https://aitranslations.io/blog/chrf-vs-bleu-wmt23-legal-task-proves-they-really-differ.php/index.md)
- [TensorFlow 2.16: XLA Fusion, Memory Pooling, and When to Upgrade](https://aitranslations.io/blog/tensorflow-216-xla-fusion-memory-pooling-and-when-to-upgrade.php/index.md)
- [2026 WMT: COMET-22's 17% Gap Switches RAG to Fine-Tuning](https://aitranslations.io/blog/2026-wmt-comet-22s-17-gap-switches-rag-to-fine-tuning.php/index.md)
- [NLLB-200 Fine-Tune Cuts Tamil Medical Drift 34% (Mean) vs GPT-4o](https://aitranslations.io/blog/nllb-200-fine-tune-cuts-tamil-medical-drift-34-mean-vs-gpt-4o.php/index.md)
- [Legal-Domain Model Outperforms Generic in MS Translator Tests](https://aitranslations.io/blog/legal-domain-model-outperforms-generic-in-ms-translator-tests.php/index.md)

Canonical: https://aitranslations.io/blog/