Machine Translation Is Not Solved: Last Translation Benchmark Released
zouharvi · x · 2026-09-04
Vilém Zouhar and collaborators argue machine translation is far from solved and release the "Last Translation Benchmark" paper on arXiv. The project uses massive crowdsourcing to collect hard-to-translate examples that break state-of-the-art translation models, enabling more reliable evaluation.
Related event: Last Translation Benchmark: 3,456 Crowdsourced Examples That Break SOTA MT(3 posts)→
More from Research
- Richard Socher: AI could compress a century of scientific breakthroughs into a decade — RichardSocher · 2026-10-21
- Startup Electric Plant builds an AI model to decipher plants' electrical signals — TechCrunch AI · 2026-10-21
- Claude reads the literature to build open human surfaceome atlas, claim by claim — owl_posting · 2026-10-20
- Eval researcher teases guide to subjective-task evals, with a curated resource list — cwolferesearch · 2026-10-20
- IIT Madras article splits LLM memory into five approaches and asks why belief revision is still missing — LimeOptimal539 · 2026-10-20
- Scholar writes AI-assisted book on storytelling values, work nominated for EMNLP best paper — _akpiper · 2026-10-20