# See the Unseen: Better Context-Consistent Knowledge-Editing by Noises

arXiv: https://arxiv.org/abs/2401.07544 · HTML: https://mlsanity.com/paper/2401.07544/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 15 Jan 2024.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (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)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [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)
- [Mind the Gap: Assessing Temporal Generalization in Neural Language Models](https://mlsanity.com/paper/2102.01951/) (2021)
- [How Context Affects Language Models' Factual Predictions](https://mlsanity.com/paper/2005.04611/) (2020)
- [PMET: Precise Model Editing in a Transformer](https://mlsanity.com/paper/2308.08742/) (2023)
- [Editable Neural Networks](https://mlsanity.com/paper/2004.00345/) (2020)
- [NEFTune: Noisy Embeddings Improve Instruction Finetuning](https://mlsanity.com/paper/2310.05914/) (2023)
- [Neurons in Large Language Models: Dead, N-gram, Positional](https://mlsanity.com/paper/2309.04827/) (2023)
- [Temporal Effects on Pre-trained Models for Language Processing Tasks](https://mlsanity.com/paper/2111.12790/) (2021)
- [NoisyTune: A Little Noise Can Help You Finetune Pretrained Language Models Better](https://mlsanity.com/paper/2202.12024/) (2022)
- [Emptying the Ocean with a Spoon: Should We Edit Models?](https://mlsanity.com/paper/2310.11958/) (2023)

## Built on by (most cited first, 5 of 5)

- [Detoxifying Large Language Models via Knowledge Editing](https://mlsanity.com/paper/2403.14472/) (2024)
- [Multi-hop Question Answering under Temporal Knowledge Editing](https://mlsanity.com/paper/2404.00492/) (2024)
- [In-Context Editing: Learning Knowledge from Self-Induced Distributions](https://mlsanity.com/paper/2406.11194/) (2024)
- [InstructEdit: Instruction-based Knowledge Editing for Large Language Models](https://mlsanity.com/paper/2402.16123/) (2024)
- [Leveraging Logical Rules in Knowledge Editing: A Cherry on the Top](https://mlsanity.com/paper/2405.15452/) (2024)

## Abstract (arXiv)

Knowledge-editing updates knowledge of large language models (LLMs) and contributes to the interpretability and application of LLMs. However, knowledge applying is context-consistent: LLMs can recall the same knowledge in different contexts. Existing works ignore this property and the editing lacks generalization. In this paper, we empirically find that the effects of different contexts upon LLMs in recalling the same knowledge follow a Gaussian-like distribution. We then sample Gaussian noises to simulate the effects of different contexts when updating LLMs. By such, we can make LLMs see the unseen contexts where the edited knowledge will be applied, therefore improving the editing generalization. Experimental results on three LLMs demonstrate the effectiveness of our methods and also distinguish our methods from the others of fine-tuning LLMs by noises.