# On the Limitations of Rank-One Model Editing in Answering Multi-hop Questions Source: [On the Limitations of Rank-One Model Editing in Answering Multi-hop Questions]() Collection index: [llms.txt]() Data updated: 2026-01-10T05:00:05.200Z Authors: Zhiyuan He, Binghan Chen, Tianxiang Xiong, Ziyang Sun, Mozhao Zhu, Xi Chen Published: 2026-01-08T05:05:09.000Z ## Abstract Recent advances in Knowledge Editing (KE), particularly Rank-One Model Editing (ROME), show superior efficiency over fine-tuning and in-context learning for updating single-hop facts in transformers. However, these methods face significant challenges when applied to multi-hop reasoning tasks requiring knowledge chaining. In this work, we study the effect of editing knowledge with ROME on different layer depths and identify three key failure modes. First, the "hopping-too-late" problem occurs as later layers lack access to necessary intermediate representations. Second, generalization ability deteriorates sharply when editing later layers. Third, the model overfits to edited knowledge, incorrectly prioritizing edited-hop answers regardless of context. To mitigate the issues of "hopping-too-late" and generalisation decay, we propose Redundant Editing, a simple yet effective strategy that enhances multi-hop reasoning. Our experiments demonstrate that this approach can improve accuracy on 2-hop questions by at least 15.5 percentage points, representing a 96% increase over the previous single-edit strategy, while trading off some specificity and language naturalness. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Multi-hop Question Answering on MQuAKE](): Multi-hop Question Answering; MQuAKE; MHQ Accuracy: 31.6. - [Knowledge Editing on Counterfact](): Knowledge Editing; CounterFact; Efficacy: 100. ## Original sources and implementation [Original paper]() [PDF]()