Parallel-SFT mixes parallel programs across languages during SFT to produce more transferable RL initializations, yielding better zero-shot generalization to unseen programming languages.
Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in P a LM ' s Translation Capability
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Multilingual pretraining develops translation in two phases: early copying driven by surface similarities, followed by generalizing mechanisms while copying is refined.
citing papers explorer
-
Parallel-SFT: Improving Zero-Shot Cross-Programming-Language Transfer for Code RL
Parallel-SFT mixes parallel programs across languages during SFT to produce more transferable RL initializations, yielding better zero-shot generalization to unseen programming languages.
-
Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining
Multilingual pretraining develops translation in two phases: early copying driven by surface similarities, followed by generalizing mechanisms while copying is refined.