paper-with-me

Papers Model Editing

“Model Editing” 태그가 달린 논문 193편 · 필터 해제

AnyEdit: Edit Any Knowledge Encoded in Language Models

2025-02-08 · Houcheng Jiang, Junfeng Fang, Ningyu Zhang, Guojun Ma 외

Large language models (LLMs) often produce incorrect or outdated information, necessitating efficient and precise knowledge updates. Current model editing methods, however, struggle with long-form knowledge in diverse fo…

FormImage Editingknowledge editingModel Editing

Cross-Encoder Rediscovers a Semantic Variant of BM25

2025-02-07 · Meng Lu, Catherine Chen, Carsten Eickhoff

Neural Ranking Models (NRMs) have rapidly advanced state-of-the-art performance on information retrieval tasks. In this work, we investigate a Cross-Encoder variant of MiniLM to determine which relevance features it comp…

Information RetrievalModel EditingRetrieval

Position: Editing Large Language Models Poses Serious Safety Risks

2025-02-05 · Paul Youssef, Zhixue Zhao, Daniel Braun, Jörg Schlötterer 외

Large Language Models (LLMs) contain large amounts of facts about the world. These facts can become outdated over time, which has led to the development of knowledge editing methods (KEs) that can change specific facts i…

knowledge editingModel EditingPosition

Efficient Model Editing with Task Vector Bases: A Theoretical Framework and Scalable Approach

2025-02-03 · Siqi Zeng, Yifei He, Weiqiu You, Yifan Hao 외

Task vectors, which are derived from the difference between pre-trained and fine-tuned model weights, enable flexible task adaptation and model merging through arithmetic operations such as addition and negation. However…

Model EditingNegationTask Arithmetic

Building Bridges, Not Walls -- Advancing Interpretability by Unifying Feature, Data, and Model Component Attribution

2025-01-31 · Shichang Zhang, Tessa Han, Usha Bhalla, Hima Lakkaraju

The increasing complexity of AI systems has made understanding their behavior a critical challenge. Numerous methods have been developed to attribute model behavior to three key aspects: input features, training data, an…

AttributeModel Editing

Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach

2025-01-19 · Jingyuan Yang, Dapeng Chen, Yajing Sun, Rongjun Li 외

A Large Language Model (LLM) tends to generate inconsistent and sometimes contradictory outputs when presented with a prompt that has equivalent semantics but is expressed differently from the original prompt. To achieve…

Large Language ModelModel EditingModel Optimization

SeaLion: Semantic Part-Aware Latent Point Diffusion Models for 3D Generation

2025-01-01 · CVPR 2025 1 · Dekai Zhu, Yan Di, Stefan Gavranovic, Slobodan Ilic

Denoising diffusion probabilistic models have achieved significant success in point cloud generation, enabling numerous downstream applications, such as generative data augmentation and 3D model editing. However, lit…

3D GenerationData AugmentationDenoisingModel Editing+2

Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification

2024-12-21 · Changchang Sun, Ren Wang, Yihua Zhang, Jinghan Jia 외

Machine unlearning (MU), which seeks to erase the influence of specific unwanted data from already-trained models, is becoming increasingly vital in model editing, particularly to comply with evolving data regulations li…

image-classificationImage ClassificationMachine UnlearningModel Editing

Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing

2024-12-17 · Keltin Grimes, Marco Christiani, David Shriver, Marissa Connor

Model editing methods modify specific behaviors of Large Language Models by altering a small, targeted set of network weights and require very little data and compute. These methods can be used for malicious applications…

MisinformationModel Editing

Model-Editing-Based Jailbreak against Safety-aligned Large Language Models

2024-12-11 · Yuxi Li, Zhibo Zhang, Kailong Wang, Ling Shi 외

Large Language Models (LLMs) have transformed numerous fields by enabling advanced natural language interactions but remain susceptible to critical vulnerabilities, particularly jailbreak attacks. Current jailbreak techn…

Model EditingSafety Alignment

Unveiling Concept Attribution in Diffusion Models

2024-12-03 · Quang H. Nguyen, Hoang Phan, Khoa D. Doan

Diffusion models have shown remarkable abilities in generating realistic and high-quality images from text prompts. However, a trained model remains black-box; little do we know about the role of its components in exhibi…

Model Editing

Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts

2024-11-23 · CVPR 2025 1 · Qizhou Chen, Chengyu Wang, Dakan Wang, Taolin Zhang 외

Model editing aims to correct inaccurate knowledge, update outdated information, and incorporate new data into Large Language Models (LLMs) without the need for retraining. This task poses challenges in lifelong scenario…

knowledge editingMixture-of-ExpertsModel Editing

Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction

2024-11-21 · Jordan Vice, Naveed Akhtar, Richard Hartley, Ajmal Mian

Training multimodal generative models on large, uncurated datasets can result in users being exposed to harmful, unsafe and controversial or culturally-inappropriate outputs. While model editing has been proposed to remo…

Image GenerationModel Editing

Model Editing for LLMs4Code: How Far are We?

2024-11-11 · Xiaopeng Li, Shangwen Wang, Shasha Li, Jun Ma 외

Large Language Models for Code (LLMs4Code) have been found to exhibit outstanding performance in the software engineering domain, especially the remarkable performance in coding tasks. However, even the most advanced LLM…

16kCode GenerationCode SummarizationContrastive Learning+5

Learning Where to Edit Vision Transformers

2024-11-04 · Yunqiao Yang, Long-Kai Huang, Shengzhuang Chen, Kede Ma 외

Model editing aims to data-efficiently correct predictive errors of large pre-trained models while ensuring generalization to neighboring failures and locality to minimize unintended effects on unrelated examples. While …

Meta-LearningModel EditingObject Recognition

Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models

2024-10-25 · Yige Li, Hanxun Huang, Jiaming Zhang, Xingjun Ma 외

Backdoor attacks covertly implant triggers into deep neural networks (DNNs) by poisoning a small portion of the training data with pre-designed backdoor triggers. This vulnerability is exacerbated in the era of large mod…

backdoor defenseModel EditingSST-2

Should We Really Edit Language Models? On the Evaluation of Edited Language Models

2024-10-24 · Qi Li, Xiang Liu, Zhenheng Tang, Peijie Dong 외

Model editing has become an increasingly popular alternative for efficiently updating knowledge within language models. Current methods mainly focus on reliability, generalization, and locality, with many methods excelli…

General KnowledgeModel Editing

Inference time LLM alignment in single and multidomain preference spectrum

2024-10-24 · Sadat Shahriar, Zheng Qi, Nikolaos Pappas, Srikanth Doss 외

Aligning Large Language Models (LLM) to address subjectivity and nuanced preference levels requires adequate flexibility and control, which can be a resource-intensive and time-consuming procedure. Existing training-time…

Model EditingPrompt Engineering

Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing

2024-10-23 · Dongliang Guo, Mengxuan Hu, Zihan Guan, Junfeng Guo 외

Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack ($\textit{i.e.,}$ backdoor attack) can manipulate the behavior o…

Adversarial AttackBackdoor AttackImage Captioningimage-classification+3

Gradient Rewiring for Editable Graph Neural Network Training

2024-10-21 · Zhimeng Jiang, Zirui Liu, Xiaotian Han, Qizhang Feng 외

Deep neural networks are ubiquitously adopted in many applications, such as computer vision, natural language processing, and graph analytics. However, well-trained neural networks can make prediction errors after deploy…

Graph Neural NetworkModel Editing
← 이전 41–60 / 193 다음 →