# KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearning

arXiv: https://arxiv.org/abs/2510.02392 · HTML: https://mlsanity.com/paper/2510.02392/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 44 of its 58 references that are in the map.
- First posted on arXiv 1 Oct 2025.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 30 of 44)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Memory-Based Model Editing at Scale](https://mlsanity.com/paper/2206.06520/) (2022)
- [Zero-Shot Relation Extraction via Reading Comprehension](https://mlsanity.com/paper/1706.04115/) (2017)
- [Editing Large Language Models: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2305.13172/) (2023)
- [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)
- [Unrolling SGD: Understanding Factors Influencing Machine Unlearning](https://mlsanity.com/paper/2109.13398/) (2021)
- [Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors](https://mlsanity.com/paper/2211.11031/) (2022)
- [MUSE: Machine Unlearning Six-Way Evaluation for Language Models](https://mlsanity.com/paper/2407.06460/) (2024)
- [Approximate Data Deletion from Machine Learning Models](https://mlsanity.com/paper/2002.10077/) (2020)
- [AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models](https://mlsanity.com/paper/2410.02355/) (2024)
- [Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?](https://mlsanity.com/paper/2405.05904/) (2024)
- [Modifying Memories in Transformer Models](https://mlsanity.com/paper/2012.00363/) (2020)
- [In-Context Unlearning: Language Models as Few Shot Unlearners](https://mlsanity.com/paper/2310.07579/) (2023)
- [Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations](https://mlsanity.com/paper/2003.02960/) (2020)
- [Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs](https://mlsanity.com/paper/2312.05934/) (2023)
- [A Comprehensive Study of Knowledge Editing for Large Language Models](https://mlsanity.com/paper/2401.01286/) (2024)
- [Editable Neural Networks](https://mlsanity.com/paper/2004.00345/) (2020)
- [Machine Unlearning of Pre-trained Large Language Models](https://mlsanity.com/paper/2402.15159/) (2024)
- [Measuring Forgetting of Memorized Training Examples](https://mlsanity.com/paper/2207.00099/) (2022)
- [Machine Unlearning: Linear Filtration for Logit-based Classifiers](https://mlsanity.com/paper/2002.02730/) (2020)
- [Model Editing at Scale leads to Gradual and Catastrophic Forgetting](https://mlsanity.com/paper/2401.07453/) (2024)

## Built on by (most cited first, 3 of 3)

- [Position: The Term "Machine Unlearning" Is Overused in LLMs](https://mlsanity.com/paper/2606.27379/) (2026)
- [A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AI](https://mlsanity.com/paper/2608.02553/) (2026)
- [SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning](https://mlsanity.com/paper/2610.01962/) (2026)

## Abstract (arXiv)

Knowledge editing and machine unlearning are two popular approaches for large language models (LLMs) to stay up-to-date. However, the knowledge updating mechanism of LLMs remains largely unexplored due to insufficient, isolated, and small-scale evaluation. For instance, are LLMs similar to humans in modifying certain knowledge? What differs editing and unlearning as training data increases? This paper proposes KnowledgeSmith, a unified framework to systematically understand the updating mechanism of LLMs. We first cast editing and unlearning as instances of one constrained optimization problem. Then, we propose an automatic dataset generator that provides structured interventions across multiple graph levels and data scales, enabling controlled studies of how different modification strategies propagate through model knowledge. Extensive experiments demonstrate nuanced insights over knowledge propagation, plasticity scaling, consistency, and robustness. For instance, our results show that LLMs do not exhibit similar updating as humans for different levels of knowledge, and there exists consistency-capacity trade-off. We hope our findings can offer suggestions to the design of more reliable and scalable strategies. Code: https://github.com/AIFrontierLab/KnowledgeSmith.git