cs.CLNov 7, 2026

On the Geometric Bottlenecks of Cross-Lingual Knowledge Editing

Authors: Aastha A K Verma, Anwoy Chatterjee, Sparsh Jain, Tanmoy Chakraborty

Organizations: Indian Institute of Technology Delhi New Delhi, India

Abstract

Transformer-based autoregressive multilingual language models (LMs) are often assumed to store factual knowledge in an interlingua: a language-agnostic latent space. If this assumption holds, a parameter update applied in a source language during knowledge editing should inherently propagate to its semantic equivalents in target languages. However, empirical benchmarks show that cross-lingual propagation of edits often degrades substantially, a degradation that prior work treats largely as an algorithmic symptom rather than a structural bottleneck. In this work, we investigate whether representational anisotropy creates a structural bottleneck for source-only associative-memory editing, and perform a geometric dissection of the cross-lingual propagation gap. Using associative memory-based "locate-then-edit" methods, including ROME, MEMIT, and AlphaEdit, as analytical frameworks, we derive a closed-form decomposition of this gap into key-space propagation, parallel residual mismatch, and orthogonal residual mismatch. Our empirical findings show that cross-lingual propagation is primarily bottlenecked by a large orthogonal residual component, indicating that source-language edits often fail to span the target-language update directions required for successful transfer. Furthermore, we show that post-hoc correction using only source-language residual statistics encounters a large residual-prediction barrier. Finally, we perform a structural realignment via a targeted contrastive alignment objective and find that it substantially improves key-space propagation and partially improves cross-lingual edit transfer, while leaving value-space mismatch as a remaining bottleneck.

Figures & tables

Appendix figures & tables19 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Orthogonal Representation Editing: Decoupling Semantic Entanglement in Batch Knowledge Editing of LLMs

    Jun 21, 2026Wenhao Yu, Zhicong Lu, Bo Lv +4Knowledge EditingModel Editing

  2. Merging Methods for Multilingual Knowledge Editing for Large Language Models: An Empirical Odyssey

    May 13, 2026Kunil Lee, Ki-Young Shin, Jong-Hyeok Lee +1Knowledge EditingMultilingual Language Models

  3. Capacity Allocation at the Source: Sparse Target Optimization for LLM Knowledge Editing

    Nov 8, 2026Dongyao Chen, Jiayun Lei, Zhiyuan Ji +3Knowledge EditingLanguage Model Editing