On the Entity-Level Alignment in Crosslingual Consistency

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Yihong, Wang, Mingyang, Yvon, François, Schütze, Hinrich
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918158767489024
author Liu, Yihong
Wang, Mingyang
Yvon, François
Schütze, Hinrich
author_facet Liu, Yihong
Wang, Mingyang
Yvon, François
Schütze, Hinrich
contents Multilingual large language models (LLMs) are expected to recall factual knowledge consistently across languages. However, the factors that give rise to such crosslingual consistency -- and its frequent failure -- remain poorly understood. In this work, we hypothesize that these inconsistencies may arise from failures in entity alignment, the process of mapping subject and object entities into a shared conceptual space across languages. To test this, we assess alignment through entity-level (subject and object) translation tasks, and find that consistency is strongly correlated with alignment across all studied models, with misalignment of subjects or objects frequently resulting in inconsistencies. Building on this insight, we propose SubSub and SubInj, two effective methods that integrate English translations of subjects into prompts across languages, leading to substantial gains in both factual recall accuracy and consistency. Finally, our mechanistic analysis reveals that these interventions reinforce the entity representation alignment in the conceptual space through model's internal pivot-language processing, offering effective and practical strategies for improving multilingual factual prediction.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10280
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the Entity-Level Alignment in Crosslingual Consistency
Liu, Yihong
Wang, Mingyang
Yvon, François
Schütze, Hinrich
Computation and Language
Multilingual large language models (LLMs) are expected to recall factual knowledge consistently across languages. However, the factors that give rise to such crosslingual consistency -- and its frequent failure -- remain poorly understood. In this work, we hypothesize that these inconsistencies may arise from failures in entity alignment, the process of mapping subject and object entities into a shared conceptual space across languages. To test this, we assess alignment through entity-level (subject and object) translation tasks, and find that consistency is strongly correlated with alignment across all studied models, with misalignment of subjects or objects frequently resulting in inconsistencies. Building on this insight, we propose SubSub and SubInj, two effective methods that integrate English translations of subjects into prompts across languages, leading to substantial gains in both factual recall accuracy and consistency. Finally, our mechanistic analysis reveals that these interventions reinforce the entity representation alignment in the conceptual space through model's internal pivot-language processing, offering effective and practical strategies for improving multilingual factual prediction.
title On the Entity-Level Alignment in Crosslingual Consistency
topic Computation and Language
url https://arxiv.org/abs/2510.10280