80%Must read
?Must readVote to see the score
ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation
ReflectMT internalizes translation reflection into direct inference via two-stage reinforcement learning, outperforming multi-step reasoning models with 94% fewer tokens.
Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026
– ReadersNo votes yet
12/20 AI panelreviewers recommend it
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
AI panel: 12 of 20 reviewers recommend it
lenient 5/5
medium 6/10
strict 1/5