MPO reduces jailbreak success in multilingual LLMs by regressing target-language reward gaps onto the English reward gap, outperforming DPO and related methods while preserving utility.
Cross-lingual Transfer of Reward Models in Multilingual Alignment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Reinforcement learning with human feedback (RLHF) is shown to largely benefit from precise reward models (RMs). However, recent studies in reward modeling schemes are skewed towards English, limiting the applicability of RLHF in multilingual alignments. In this work, we investigate the cross-lingual transfer of RMs trained in diverse languages, primarily from English. Our experimental results demonstrate the strong cross-lingual transfer of English RMs, exceeding target language RMs by 3~4% average increase in Multilingual RewardBench. Furthermore, we analyze the cross-lingual transfer of RMs through the representation shifts. Finally, we perform multilingual alignment to exemplify how cross-lingual transfer in RM propagates to enhanced multilingual instruction-following capability, along with extensive analyses on off-the-shelf RMs. We release the code, model, and data.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MPO: Multilingual Safety Alignment via Reward Gap Optimization
MPO reduces jailbreak success in multilingual LLMs by regressing target-language reward gaps onto the English reward gap, outperforming DPO and related methods while preserving utility.