# Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject

arXiv: https://arxiv.org/abs/2502.06868 · HTML: https://mlsanity.com/paper/2502.06868/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 8 Feb 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 8 of 8)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue](https://mlsanity.com/paper/2401.04700/) (2024)
- [EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models](https://mlsanity.com/paper/2308.07269/) (2023)
- [The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse](https://mlsanity.com/paper/2402.09656/) (2024)
- [Understanding the Collapse of LLMs in Model Editing](https://mlsanity.com/paper/2406.11263/) (2024)

## Built on by (most cited first, 10 of 10)

- [Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking](https://mlsanity.com/paper/2503.19602/) (2025)
- [Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment](https://mlsanity.com/paper/2502.11401/) (2025)
- [Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning](https://mlsanity.com/paper/2509.06461/) (2025)
- [Gated Differentiable Working Memory for Long-Context Language Modeling](https://mlsanity.com/paper/2601.12906/) (2026)
- [Large Language Model Sourcing: A Survey](https://mlsanity.com/paper/2510.10161/) (2025)
- [Circular Reasoning: Understanding Self-Reinforcing Loops in Large Reasoning Models](https://mlsanity.com/paper/2601.05693/) (2026)
- [Beyond the Covariance Trap: Unlocking Generalization in Same-Subject Knowledge Editing for Large Language Models](https://mlsanity.com/paper/2603.15518/) (2026)
- [Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models](https://mlsanity.com/paper/2511.04053/) (2025)
- [Conflict-Resolving and Sharpness-Aware Minimization for Generalized Knowledge Editing with Multiple Updates](https://mlsanity.com/paper/2602.03696/) (2026)
- [ALOE: Semantically Addressed Low-Rank Operators for Knowledge Editing](https://mlsanity.com/paper/2609.29269/) (2026)

## Abstract (arXiv)

Knowledge editing has become a promising approach for efficiently and precisely updating knowledge embedded in large language models (LLMs). In this work, we focus on Same-Subject Editing, which involves modifying multiple attributes of a single entity to ensure comprehensive and consistent updates to entity-centric knowledge. Through preliminary observation, we identify a significant challenge: Current state-of-the-art editing methods struggle when tasked with editing multiple related knowledge pieces for the same subject. To address the lack of relevant editing data for identical subjects in traditional benchmarks, we introduce the S2RKE(Same-Subject Related Knowledge Editing) benchmark. Our extensive experiments reveal that only mainstream locate-then-edit methods, such as ROME and MEMIT, exhibit "related knowledge perturbation," where subsequent edits interfere with earlier ones. Further analysis reveals that these methods over-rely on subject information, neglecting other critical factors, resulting in reduced editing effectiveness.