# Knowledge Editing in Language Models via Adapted Direct Preference Optimization

arXiv: https://arxiv.org/abs/2406.09920 · HTML: https://mlsanity.com/paper/2406.09920/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 24 of its 28 references that are in the map.
- First posted on arXiv 14 Jun 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 24 of 24)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [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)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Editing Large Language Models: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2305.13172/) (2023)
- [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://mlsanity.com/paper/2302.12813/) (2023)
- [Can We Edit Factual Knowledge by In-Context Learning?](https://mlsanity.com/paper/2305.12740/) (2023)
- [Knowledge Editing for Large Language Models: A Survey](https://mlsanity.com/paper/2310.16218/) (2023)
- [PMET: Precise Model Editing in a Transformer](https://mlsanity.com/paper/2308.08742/) (2023)
- [A Comprehensive Study of Knowledge Editing for Large Language Models](https://mlsanity.com/paper/2401.01286/) (2024)
- [Factuality Challenges in the Era of Large Language Models](https://mlsanity.com/paper/2310.05189/) (2023)
- [Combating Misinformation in the Age of LLMs: Opportunities and Challenges](https://mlsanity.com/paper/2311.05656/) (2023)
- [How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances](https://mlsanity.com/paper/2310.07343/) (2023)

## Built on by (most cited first, 17 of 17)

- [In-Context Editing: Learning Knowledge from Self-Induced Distributions](https://mlsanity.com/paper/2406.11194/) (2024)
- [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)
- [SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training](https://mlsanity.com/paper/2505.24749/) (2025)
- [AdaRankGrad: Adaptive Gradient-Rank and Moments for Memory-Efficient LLMs Training and Fine-Tuning](https://mlsanity.com/paper/2410.17881/) (2024)
- [Position: Editing Large Language Models Poses Serious Safety Risks](https://mlsanity.com/paper/2502.02958/) (2025)
- [CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners](https://mlsanity.com/paper/2503.16356/) (2025)
- [Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing](https://mlsanity.com/paper/2502.00602/) (2025)
- [LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models](https://mlsanity.com/paper/2409.13054/) (2024)
- [LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM](https://mlsanity.com/paper/2502.19571/) (2025)
- [FineGates: LLMs Finetuning with Compression using Stochastic Gates](https://mlsanity.com/paper/2412.12951/) (2024)
- [Flying Pigs, FaR and Beyond: Evaluating LLM Reasoning in Counterfactual Worlds](https://mlsanity.com/paper/2505.22318/) (2025)
- [TransformLLM: Adapting Large Language Models via LLM-Transformed Reading Comprehension Text](https://mlsanity.com/paper/2410.21479/) (2024)
- [Train Less, Infer Faster: Efficient Model Finetuning and Compression via Structured Sparsity](https://mlsanity.com/paper/2602.09169/) (2026)
- [EtCon: Edit-then-Consolidate for Reliable Knowledge Editing](https://mlsanity.com/paper/2512.04753/) (2025)
- [Synthetic Worlds for Temporal Evaluation and Knowledge Updating in LLMs](https://mlsanity.com/paper/2609.00184/) (2026)
- [Style-Debiased DPO: Updating LLM Knowledge with Factuality-Aware Synthetic Preference Data](https://mlsanity.com/paper/2609.16532/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) can become outdated over time as they may lack updated world knowledge, leading to factual knowledge errors and gaps. Knowledge Editing (KE) aims to overcome this challenge using weight updates that do not require expensive retraining. We propose treating KE as an LLM alignment problem. Toward this goal, we introduce Knowledge Direct Preference Optimization (KDPO), a variation of the Direct Preference Optimization (DPO) that is more effective for knowledge modifications. Our method is based on an online approach that continually updates the knowledge stored in the model. We use the current knowledge as a negative sample and the new knowledge we want to introduce as a positive sample in a process called DPO. We also use teacher-forcing for negative sample generation and optimize using the positive sample, which helps maintain localized changes. We tested our KE method on various datasets and models, comparing it to several cutting-edge methods, with 100 and 500 sequential edits. Additionally, we conducted an ablation study comparing our method to the standard DPO approach. Our experimental results show that our modified DPO method allows for more refined KE, achieving similar or better performance compared to previous methods.