Applying Wasserstein-distance domain adaptation, a known technique, to reward models lets preference signals learned on labeled source data transfer to unlabeled target domains, with consistent but modest gains across four settings.
Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Aligning language models (LMs) based on human-annotated preference data is a crucial step in obtaining practical and performant LM-based systems. However, multilingual human preference data are difficult to obtain at scale, making it challenging to extend this framework to diverse languages. In this work, we evaluate a simple approach for zero-shot cross-lingual alignment, where a reward model is trained on preference data in one source language and directly applied to other target languages. On summarization and open-ended dialog generation, we show that this method is consistently successful under comprehensive evaluation settings, including human evaluation: cross-lingually aligned models are preferred by humans over unaligned models on up to >70% of evaluation instances. We moreover find that a different-language reward model sometimes yields better aligned models than a same-language reward model. We also identify best practices when there is no language-specific data for even supervised finetuning, another component in alignment.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Aligning LLMs with Domain Invariant Reward Models
Applying Wasserstein-distance domain adaptation, a known technique, to reward models lets preference signals learned on labeled source data transfer to unlabeled target domains, with consistent but modest gains across four settings.