SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.18027 · 2024

Cross-lingual Transfer of Reward Models in Multilingual Alignment

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
iq-kaist/rm-lingual-transfer canonical 1 of 2
FunctionStatusWhere it lives
is_openai_format Ran iq-kaist/rm-lingual-transfer/src/utils.py
code served (permissive licence) · get_code("4253aac010c4504f")
map_chat_template_by_task Not yet run iq-kaist/rm-lingual-transfer/src/utils.py
code served (permissive licence) · get_code("85071a4f3ab5213e")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.18027")
get_code_for_paper("2410.18027")
have("2410.18027")

Connect an agent — have() is free.