# How Well Can Knowledge Edit Methods Edit Perplexing Knowledge?

arXiv: https://arxiv.org/abs/2406.17253 · HTML: https://mlsanity.com/paper/2406.17253/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 28 references that are in the map.
- First posted on arXiv 25 Jun 2024.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Knowledge Neurons in Pretrained Transformers](https://mlsanity.com/paper/2104.08696/) (2021)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions](https://mlsanity.com/paper/2305.14795/) (2023)
- [Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models](https://mlsanity.com/paper/2301.04213/) (2023)
- [Evaluating the Ripple Effects of Knowledge Editing in Language Models](https://mlsanity.com/paper/2307.12976/) (2023)
- [Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledge](https://mlsanity.com/paper/2305.01651/) (2023)
- [Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark](https://mlsanity.com/paper/2305.17553/) (2023)
- [What does the Knowledge Neuron Thesis Have to do with Knowledge?](https://mlsanity.com/paper/2405.02421/) (2024)
- [Knowledge Graph Enhanced Large Language Model Editing](https://mlsanity.com/paper/2402.13593/) (2024)
- [Editing Common Sense in Transformers](https://mlsanity.com/paper/2305.14956/) (2023)
- [Long-form evaluation of model editing](https://mlsanity.com/paper/2402.09394/) (2024)
- [Editing Conceptual Knowledge for Large Language Models](https://mlsanity.com/paper/2403.06259/) (2024)
- [Evaluating Dependencies in Fact Editing for Language Models: Specificity and Implication Awareness](https://mlsanity.com/paper/2312.01858/) (2023)

## Built on by (most cited first, 4 of 4)

- [Can Knowledge Editing Really Correct Hallucinations?](https://mlsanity.com/paper/2410.16251/) (2024)
- [Can Editing LLMs Inject Harm?](https://mlsanity.com/paper/2407.20224/) (2024)
- [PIS: Linking Importance Sampling and Attention Mechanisms for Efficient Prompt Compression](https://mlsanity.com/paper/2504.16574/) (2025)
- [PROMPT2BOX:Improving LLM Weakness Discovery and Specificity Estimation by Uncovering Entailment Structure among Prompts](https://mlsanity.com/paper/2603.21438/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated remarkable capabilities, but updating their knowledge post-training remains a critical challenge. While recent model editing techniques like Rank-One Model Editing (ROME) show promise, their effectiveness may vary based on the nature of the knowledge being edited. We introduce the concept of ``perplexingness'': the degree to which new knowledge conflicts with an LLM's learned conceptual hierarchies and categorical relationships. For instance, editing ``British Shorthair is a kind of cat'' to ``British Shorthair is a kind of dog'' represents a low-perplexingness edit within the same taxonomic level, while editing ``A cat is a kind of animal'' to ``A cat is a kind of plant'' represents a high-perplexingness edit that violates fundamental categorical boundaries. To systematically investigate this phenomenon, we introduce HierarchyData, a carefully curated dataset of 99 hyponym-hypernym pairs across diverse categories. Through controlled experiments across three models and four editing methods, we demonstrate a strong negative correlation between the perplexingness of new knowledge and the effectiveness of knowledge editing. Our analysis reveals that edits involving more abstract concepts (hypernyms) generally exhibit higher perplexingness and are more resistant to modification than their specific counterparts (hyponyms). These findings highlight a fundamental challenge in LLM knowledge editing: the more a new fact contradicts an LLM's learned conceptual hierarchies, the harder it becomes to reliably encode that knowledge.