O-Edit: Orthogonal Subspace Editing for Language Model Sequential Editing
- URL: http://arxiv.org/abs/2410.11469v1
- Date: Tue, 15 Oct 2024 10:16:45 GMT
- Title: O-Edit: Orthogonal Subspace Editing for Language Model Sequential Editing
- Authors: Yuchen Cai, Ding Cao,
- Abstract summary: Large language models (LLMs) acquire knowledge during pre-training, but over time, this knowledge may become incorrect or outdated, necessitating updates after training.
We propose Orthogonal Subspace Editing, O-Edit. This algorithmizes the direction of each knowledge update, minimizing interference between successive updates and reducing the impact of new updates on unrelated knowledge.
It can perform thousands of edits on mainstream LLMs, achieving an average performance improvement that is 4.2 times better than existing methods while effectively preserving the model's performance on downstream tasks, all with minimal additional parameter overhead.
- Score: 0.0
- License:
- Abstract: Large language models (LLMs) acquire knowledge during pre-training, but over time, this knowledge may become incorrect or outdated, necessitating updates after training. Knowledge editing techniques address this issue without the need for costly re-training. However, most existing methods are designed for single edits, and as the number of edits increases, they often cause a decline in the model's overall performance, posing significant challenges for sequential editing. To overcome this, we propose Orthogonal Subspace Editing, O-Edit. This algorithm orthogonalizes the direction of each knowledge update, minimizing interference between successive updates and reducing the impact of new updates on unrelated knowledge. Our approach does not require replaying previously edited data and processes each edit knowledge on time. It can perform thousands of edits on mainstream LLMs, achieving an average performance improvement that is 4.2 times better than existing methods while effectively preserving the model's performance on downstream tasks, all with minimal additional parameter overhead.
Related papers
- K-Edit: Language Model Editing with Contextual Knowledge Awareness [71.73747181407323]
Knowledge-based model editing enables precise modifications to the weights of large language models.
We present K-Edit, an effective approach to generating contextually consistent knowledge edits.
arXiv Detail & Related papers (2025-02-15T01:35:13Z) - Reinforced Lifelong Editing for Language Models [12.101856766731574]
Large language models (LLMs) acquire information from pre-training corpora, but their stored knowledge can become inaccurate or outdated over time.
Model editing addresses this challenge by modifying model parameters without retraining, and prevalent approaches leverage hypernetworks to generate these parameter updates.
We propose RLEdit, an RL-based editing method that captures changes at the full knowledge sequence level and generates appropriate parameter updates.
arXiv Detail & Related papers (2025-02-09T03:37:06Z) - AnyEdit: Edit Any Knowledge Encoded in Language Models [69.30638272162267]
We propose AnyEdit, a new autoregressive editing paradigm for large language models (LLMs)
It decomposes long-form knowledge into sequential chunks and iteratively edits the key token in each chunk, ensuring consistent and accurate outputs.
It outperforms strong baselines by 21.5% on benchmarks including UnKEBench, AKEW, and our new EditEverything dataset for long-form diverse-formatted knowledge.
arXiv Detail & Related papers (2025-02-08T16:18:37Z) - Knowledge Editing through Chain-of-Thought [12.270274049887298]
Large Language Models (LLMs) have demonstrated exceptional capabilities across a wide range of natural language processing (NLP) tasks.
Keeping these models up-to-date with evolving world knowledge remains a significant challenge due to the high costs of frequent retraining.
We propose EditCoT, a novel knowledge editing framework that flexibly and efficiently updates LLMs across various tasks without retraining.
arXiv Detail & Related papers (2024-12-23T17:17:50Z) - Neuron-Level Sequential Editing for Large Language Models [19.324852774144752]
We introduce textbfNeuron-level textbfSequential textbfEditing (NSE) for supporting sequential model editing.
Specifically, we optimize the target layer's hidden states using the model's original weights to prevent model failure.
Our experiments demonstrate that NSE significantly outperforms current modifying parameters model editing methods.
arXiv Detail & Related papers (2024-10-05T05:52:22Z) - ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA [55.697627106315004]
Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors.
Previous approaches manage sequential edits by freezing original parameters and discretely allocating new parameters for each knowledge update.
We propose ELDER, a novel approach to create a continuous association between data and adapters.
arXiv Detail & Related papers (2024-08-19T02:27:00Z) - SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering [17.20346072074533]
Recent model editing is a promising technique for efficiently updating a small amount of knowledge of large language models.
We propose a detachable and expandable Subject Word Embedding Altering (SWEA) framework, which finds the editing embeddings through token-level matching.
We demonstrate the overall state-of-the-art (SOTA) performance of SWEA$oplus$OS on the CounterFact and zsRE datasets.
arXiv Detail & Related papers (2024-01-31T13:08:45Z) - Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue [122.20016030723043]
We evaluate the side effects of model editing on large language models (LLMs)
Our analysis reveals that the side effects are caused by model editing altering the original model weights excessively.
To mitigate this, a method named RECT is proposed to regularize the edit update weights.
arXiv Detail & Related papers (2024-01-09T18:03:15Z) - Aging with GRACE: Lifelong Model Editing with Discrete Key-Value
Adaptors [53.819805242367345]
We propose GRACE, a lifelong model editing method, which implements spot-fixes on streaming errors of a deployed model.
GRACE writes new mappings into a pre-trained model's latent space, creating a discrete, local codebook of edits without altering model weights.
Our experiments on T5, BERT, and GPT models show GRACE's state-of-the-art performance in making and retaining edits, while generalizing to unseen inputs.
arXiv Detail & Related papers (2022-11-20T17:18:22Z) - Memory-Based Model Editing at Scale [102.28475739907498]
Existing model editors struggle to accurately model an edit's intended scope.
We propose Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model (SERAC)
SERAC stores edits in an explicit memory and learns to reason over them to modulate the base model's predictions as needed.
arXiv Detail & Related papers (2022-06-13T23:40:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.