# Does Knowledge Localization Hold True? Surprising Differences Between Entity and Relation Perspectives in Language Models

arXiv: https://arxiv.org/abs/2409.00617 · HTML: https://mlsanity.com/paper/2409.00617/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 21 references that are in the map.
- First posted on arXiv 1 Sep 2024.

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

- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [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)
- [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)
- [Can We Edit Factual Knowledge by In-Context Learning?](https://mlsanity.com/paper/2305.12740/) (2023)
- [Transformer-Patcher: One Mistake worth One Neuron](https://mlsanity.com/paper/2301.09785/) (2023)
- [Calibrating Factual Knowledge in Pretrained Language Models](https://mlsanity.com/paper/2210.03329/) (2022)
- [Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons](https://mlsanity.com/paper/2308.13198/) (2023)
- [Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent](https://mlsanity.com/paper/2402.13717/) (2024)
- [EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification](https://mlsanity.com/paper/2310.09754/) (2023)
- [LingYi: Medical Conversational Question Answering System based on Multi-modal Knowledge Graphs](https://mlsanity.com/paper/2204.09220/) (2022)
- [MenatQA: A New Dataset for Testing the Temporal Comprehension and Reasoning Abilities of Large Language Models](https://mlsanity.com/paper/2310.05157/) (2023)
- [Knowledge Localization: Mission Not Accomplished? Enter Query Localization!](https://mlsanity.com/paper/2405.14117/) (2024)
- [Relational Prompt-based Pre-trained Language Models for Social Event Detection](https://mlsanity.com/paper/2404.08263/) (2024)

## Built on by (most cited first, 9 of 9)

- [DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively](https://mlsanity.com/paper/2509.26603/) (2025)
- [Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes](https://mlsanity.com/paper/2410.16930/) (2024)
- [Fine-tuning Done Right in Model Editing](https://mlsanity.com/paper/2509.22072/) (2025)
- [Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency](https://mlsanity.com/paper/2603.17102/) (2026)
- [SetKE: Knowledge Editing for Knowledge Elements Overlap](https://mlsanity.com/paper/2504.20972/) (2025)
- [A Semantic-based Optimization Approach for Repairing LLMs: Case Study on Code Generation](https://mlsanity.com/paper/2503.12899/) (2025)
- [Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis](https://mlsanity.com/paper/2602.20207/) (2026)
- [Fine-Tuning Dynamics of In-Context Factual Recall in Transformers](https://mlsanity.com/paper/2605.27774/) (2026)
- [Through the Looking Glass: Directly Reading and Writing Transformers](https://mlsanity.com/paper/2609.10210/) (2026)

## Abstract (arXiv)

Large language models encapsulate knowledge and have demonstrated superior performance on various natural language processing tasks. Recent studies have localized this knowledge to specific model parameters, such as the MLP weights in intermediate layers. This study investigates the differences between entity and relational knowledge through knowledge editing. Our findings reveal that entity and relational knowledge cannot be directly transferred or mapped to each other. This result is unexpected, as logically, modifying the entity or the relation within the same knowledge triplet should yield equivalent outcomes. To further elucidate the differences between entity and relational knowledge, we employ causal analysis to investigate how relational knowledge is stored in pre-trained models. Contrary to prior research suggesting that knowledge is stored in MLP weights, our experiments demonstrate that relational knowledge is also significantly encoded in attention modules. This insight highlights the multifaceted nature of knowledge storage in language models, underscoring the complexity of manipulating specific types of knowledge within these models.