CSPF: A Constrained Shared-Private Fusion Method for Non-Verifiable Preference Evaluation 文章

ArXiv CS.CL2026-07-24PAPERen作者: Hehao Zhang, Danli Wang, Xinyuan Wang, Xuange Gao

详细信息

来源站点
ArXiv CS.CL
作者
Hehao Zhang, Danli Wang, Xinyuan Wang, Xuange Gao
文章类型
PAPER
语言
en
发布日期
2026-07-24

摘要

arXiv:2607.20862v1 Announce Type: new Abstract: At present, reliable evaluation of non-verifiable tasks remains challenging. Existing approaches often fail to adequately capture the diverse evaluative criteria underlying human preferences in such tasks. To this end, we propose Constrained Shared-Private Fusion (CSPF), a fusion method that treats heterogeneous frozen reward models as complementary evaluators and learns to integrate their hidden-state representations under pairwise human-preference supervision. CSPF decomposes each expert signal into shared and expert-private representations, encouraging cross-expert alignment while preserving complementary viewpoints. Across experiments on LM-Arena target-domain adaptation and PPE out-of-distribution preference evaluation, CSPF achieves the best performance on the primary metrics among the evaluated single-expert reward-model, scalar-score multi-expert, and rubric-judge baselines.

相关事件

暂无数据

相关公司

暂无数据

相关人物

暂无数据