← back to paper

Review history

arxiv: 2608.03577 · 2 revisions

Looking under the Wrong Lamppost: On the Limitations of Automated Translation Quality Estimation

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 5.0
   125900 ms 13272 in 15538 out 2026-08-15T14:48:41.507003+00:00
2. 2026-08-05 CONDITIONAL MODERATE v1.4.0-daily-deepseek-medium novelty 4.0
   207798 ms 13246 in 17869 out 2026-08-05T16:38:15.359806+00:00