Zero-human pipeline produces best system in WMT Creole MT shared task
anas_ant · x · 2026-11-06
The author reports using the same fully automated pipeline (zero human intervention) for this year's WMT Creole MT Shared Task, producing the best system in some language pairs. The work took 6 years but only became feasible with today's models; data, models and a detailed write-up are released, with more languages planned.
More from Research
- Stanford paper proposes differentially private watermarks for LLMs — ChengleiSi · 2026-11-06
- Stanford PhD JulieKallini on testing Chomsky: can LMs learn a language no human could? — ChrisGPotts · 2026-11-06
- Exo paper: agents that rewrite their own harness at runtime, cutting model cost up to 82% — sarahcat21 · 2026-11-06
- Study: LLMs Notice Context Conflicts 73% of the Time but Tell Users 0% — rseroter · 2026-11-06
- Science's Last Exam: best of 8 frontier models scores 37.5/100, all score 0 on end-to-end research — anshulkundaje · 2026-11-06
- Tokenizer Myths and Where To Find Them: Stanford paper debunks three BPB myths — rohanpaul_ai · 2026-11-06