Papers Model Editing
“Model Editing” 태그가 달린 논문 193편 · 필터 해제
Mitigating Gender Bias in Code Large Language Models via Model Editing
In recent years, with the maturation of large language model (LLM) technology and the emergence of high-quality programming code datasets, researchers have become increasingly confident in addressing the challenges of pr…
Code Generationknowledge editingLarge Language ModelModel Editing+1Uncovering Overfitting in Large Language Model Editing
Knowledge editing has been proposed as an effective method for updating and correcting the internal knowledge of Large Language Models (LLMs). However, existing editing methods often struggle with complex tasks, such as …
AttributeIn-Context Learningknowledge editingLanguage Modeling+4Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing
Large Language Models (LLMs) have recently revolutionized the NLP field, while they still fall short in some specific down-stream tasks. In the work, we focus on utilizing LLMs to perform machine translation, where we ob…
Machine TranslationModel EditingTranslationFAME: Towards Factual Multi-Task Model Editing
Large language models (LLMs) embed extensive knowledge and utilize it to perform exceptionally well across various tasks. Nevertheless, outdated knowledge or factual errors within LLMs can lead to misleading or incorrect…
modelModel EditingNeuron-Level Sequential Editing for Large Language Models
This work explores sequential model editing in large language models (LLMs), a critical task that involves modifying internal knowledge within LLMs continuously through multi-round editing, each incorporating updates or …
Model EditingAlphaEdit: Null-Space Constrained Knowledge Editing for Language Models
Large language models (LLMs) often exhibit hallucinations due to incorrect or outdated knowledge. Hence, model editing methods have emerged to enable targeted knowledge updates. To achieve this, a prevailing paradigm is …
knowledge editingModel EditingBetter Call SAUL: Fluent and Consistent Language Model Editing with Generation Regularization
To ensure large language models contain up-to-date knowledge, they need to be updated regularly. However, model editing is challenging as it might also affect knowledge that is unrelated to the new data. State-of-the-art…
Language ModelingLanguage ModellingModel EditingSentenceUniAdapt: A Universal Adapter for Knowledge Calibration
Large Language Models (LLMs) require frequent updates to correct errors and keep pace with continuously evolving knowledge in a timely and effective manner. Recent research in it model editing has highlighted the challen…
Mixture-of-ExpertsModel EditingRetrieval-augmented GenerationSemantic Similarity+1Self-Updatable Large Language Models with Parameter Integration
Despite significant advancements in large language models (LLMs), the rapid and frequent integration of small-scale experiences, such as interactions with surrounding objects, remains a substantial challenge. Two critica…
Continual LearningConversational RecommendationKnowledge DistillationModel Editing+1"Why" Has the Least Side Effect on Model Editing
Training large language models (LLMs) from scratch is an expensive endeavor, particularly as world knowledge continually evolves. To maintain relevance and accuracy of LLMs, model editing has emerged as a pivotal researc…
Experimental Designknowledge editingModel EditingWorld KnowledgeInterpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis
We find arithmetic ability resides within a limited number of attention heads, with each head specializing in distinct operations. To delve into the reason, we introduce the Comparative Neuron Analysis (CNA) method, whic…
Model EditingPredictionProperty Neurons in Self-Supervised Speech Transformers
There have been many studies on analyzing self-supervised speech Transformers, in particular, with layer-wise analysis. It is, however, desirable to have an approach that can pinpoint exactly a subset of neurons that is …
Model EditingTimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model
With recent advances in building foundation models for texts and video data, there is a surge of interest in foundation models for time series. A family of models have been developed, utilizing a temporal auto-regressive…
Anomaly DetectionDenoisingImputationMissing Values+2Enhancing Multi-hop Reasoning through Knowledge Erasure in Large Language Model Editing
Large language models (LLMs) face challenges with internal knowledge inaccuracies and outdated information. Knowledge editing has emerged as a pivotal approach to mitigate these issues. Although current knowledge editing…
knowledge editingLanguage ModelingLanguage ModellingLarge Language Model+1MEGen: Generative Backdoor in Large Language Models via Model Editing
Large language models (LLMs) have demonstrated remarkable capabilities. Their powerful generative abilities enable flexible responses based on various queries or instructions. Emerging as widely adopted generalists for d…
Backdoor AttackLanguage ModellingModel EditingPromoting Equality in Large Language Models: Identifying and Mitigating the Implicit Bias based on Bayesian Theory
Large language models (LLMs) are trained on extensive text corpora, which inevitably include biased information. Although techniques such as Affective Alignment can mitigate some negative impacts of these biases, existin…
Model EditingAttribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit
Model editing aims to correct outdated or erroneous knowledge in large models without costly retraining. Recent research discovered that the mid-layer representation of the subject's final token in a prompt has a strong …
DecoderLanguage ModelingLanguage ModellingLarge Language Model+1Resolving Lexical Bias in Edit Scoping with Projector Editor Networks
Weight-preserving model editing techniques heavily rely on the scoping mechanism that decides when to apply an edit to the base model. These scoping mechanisms utilize distance functions in the representation space to as…
Contrastive LearningModel EditingELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA
Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors. Most model editing methods are solely designed for single-time use and result in a signifi…
Model EditingCan LLMs be Fooled? Investigating Vulnerabilities in LLMs
The advent of Large Language Models (LLMs) has garnered significant popularity and wielded immense power across various domains within Natural Language Processing (NLP). While their capabilities are undeniably impressive…
Model Editing