Memory-Based Model Editing at Scale
- URL: http://arxiv.org/abs/2206.06520v1
- Date: Mon, 13 Jun 2022 23:40:34 GMT
- Title: Memory-Based Model Editing at Scale
- Authors: Eric Mitchell, Charles Lin, Antoine Bosselut, Christopher D. Manning,
Chelsea Finn
- Abstract summary: 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.
- Score: 102.28475739907498
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Even the largest neural networks make errors, and once-correct predictions
can become invalid as the world changes. Model editors make local updates to
the behavior of base (pre-trained) models to inject updated knowledge or
correct undesirable behaviors. Existing model editors have shown promise, but
also suffer from insufficient expressiveness: they struggle to accurately model
an edit's intended scope (examples affected by the edit), leading to inaccurate
predictions for test inputs loosely related to the edit, and they often fail
altogether after many edits. As a higher-capacity alternative, we propose
Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model
(SERAC), which stores edits in an explicit memory and learns to reason over
them to modulate the base model's predictions as needed. To enable more
rigorous evaluation of model editors, we introduce three challenging language
model editing problems based on question answering, fact-checking, and dialogue
generation. We find that only SERAC achieves high performance on all three
problems, consistently outperforming existing approaches to model editing by a
significant margin. Code, data, and additional project information will be made
available at https://sites.google.com/view/serac-editing.
Related papers
- Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs? [61.68363765350178]
This paper critiques the standard formulation of the model editing problem and proposes a formal testbed for model editing research.
We first describe 12 open problems with model editing, based on challenges with (1) defining the problem, (2) developing benchmarks, and (3) assuming LLMs have editable beliefs in the first place.
Next, we introduce a semi-synthetic dataset for model editing based on Wikidata, where we can evaluate edits against labels given by an idealized Bayesian agent.
arXiv Detail & Related papers (2024-06-27T17:33:03Z) - The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse [58.0132400208411]
Even a single edit can trigger model collapse, manifesting as significant performance degradation in various benchmark tasks.
benchmarking Large Language Models after each edit is impractically time-consuming and resource-intensive.
We have utilized GPT-3.5 to develop a new dataset, HardEdit, based on hard cases.
arXiv Detail & Related papers (2024-02-15T01:50:38Z) - Model Editing at Scale leads to Gradual and Catastrophic Forgetting [2.569159339315845]
We evaluate the current model editing methods at scale, focusing on two state of the art methods: ROME and MEMIT.
We find that as the model is edited sequentially with multiple facts, it continually forgets previously edited facts and the ability to perform downstream tasks.
arXiv Detail & Related papers (2024-01-15T03:57:15Z) - Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue [122.20016030723043]
Model editing is a technique that edits large language models (LLMs) with updated knowledge to alleviate hallucinations without resource-intensive retraining.
Current model editing methods can effectively modify a model's behavior within a specific area of interest.
They often overlook the potential unintended side effects on the general abilities of LLMs.
arXiv Detail & Related papers (2024-01-09T18:03:15Z) - Edit at your own risk: evaluating the robustness of edited models to
distribution shifts [0.0]
We investigate how model editing affects the general robustness of a model, as well as the robustness of the specific behavior targeted by the edit.
We find that edits tend to reduce general robustness, but that the degree of degradation depends on the editing algorithm and layers chosen.
Motivated by these observations we introduce a new model editing algorithm, 1-layer (1-LI), which uses weight-space to navigate the trade-off between editing task accuracy and general robustness.
arXiv Detail & Related papers (2023-02-28T19:41:37Z) - 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) - Fast Model Editing at Scale [77.69220974621425]
We propose Model Editor Networks with Gradient Decomposition (MEND)
MEND is a collection of small auxiliary editing networks that use a single desired input-output pair to make fast, local edits to a pre-trained model.
MEND can be trained on a single GPU in less than a day even for 10 billion+ parameter models.
arXiv Detail & Related papers (2021-10-21T17:41:56Z) - A Structural Model for Contextual Code Changes [20.185486717922615]
Given a code snippet that is partially edited, our goal is to predict a completion of the edit for the rest of the snippet.
Our model achieves a 28% relative gain over state-of-the-art sequential models and 2x higher accuracy than syntactic models that learn to generate the edited code.
arXiv Detail & Related papers (2020-05-27T07:16:19Z)
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.