홈 › Papers

Latent Knowledge Scalpel: Precise and Massive Knowledge Editing for Large Language Models

2025-08-01 · Xin Liu, Qiyang Song, Shaowen Xu, Kerou Zhou, Wenbo Jiang, Xiaoqi Jia, Weijuan Zhang, Heqing Huang, Yakai Li arxiv

Large Language Models (LLMs) often retain inaccurate or outdated information from pre-training, leading to incorrect predictions or biased outputs during inference. While existing model editing methods can address this challenge, they struggle with editing large amounts of factual information simultaneously and may compromise the general capabilities of the models. In this paper, our empirical study demonstrates that it is feasible to edit the internal representations of LLMs and replace the entities in a manner similar to editing natural language inputs. Based on this insight, we introduce the Latent Knowledge Scalpel (LKS), an LLM editor that manipulates the latent knowledge of specific entities via a lightweight hypernetwork to enable precise and large-scale editing. Experiments conducted on Llama-2 and Mistral show even with the number of simultaneous edits reaching 10,000, LKS effectively performs knowledge editing while preserving the general abilities of the edited LLMs. Code is available at: https://github.com/Linuxin-xxx/LKS.

📄 PDF Abstract BibTeX arXiv:2508.03741

Code (0)

등록된 구현이 없습니다.

Tasks

knowledge editing

Scalpel-SAM: A Semi-Supervised Paradigm for Adapting SAM to Infrared Small Object Detection

2025-12-27 · Zihan Liu, Xiangning Ren, Dezhang Kong, Yipeng Zhang 외 arxiv

Infrared small object detection urgently requires semi-supervised paradigms due to the high cost of annotation. However, existing methods like SAM face significant challenges of domain gaps, inability of encoding physica…

Knowledge Distillation Small Object Detection

Scalpel: Fine-Grained Alignment of Attention Activation Manifolds via Mixture Gaussian Bridges to Mitigate Multimodal Hallucination

2026-02-10 · Ziqiang Shi, Rujie Liu, Shanshan Yu, Satoshi Munakata 외 arxiv

Rapid progress in large vision-language models (LVLMs) has achieved unprecedented performance in vision-language tasks. However, due to the strong prior of large language models (LLMs) and misaligned attention across mod…

Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias

2023-05-08 · Zhiyuan Zhang, Deli Chen, Hao Zhou, Fandong Meng 외

Pre-trained Language Models (PLMs) may be poisonous with backdoors or bias injected by the suspicious attacker during the fine-tuning process. A core challenge of purifying potentially poisonous PLMs is precisely finding…

SCALPEL: Selective Capability Ablation via Low-rank Parameter Editing for Large Language Model Interpretability Analysis

2026-01-12 · Zihao Fu, Xufeng Duan, Zhenguang G. Cai arxiv

Large language models excel across diverse domains, yet their deployment in healthcare, legal systems, and autonomous decision-making remains limited by incomplete understanding of their internal mechanisms. As these mod…

Spectral Scalpel: Amplifying Adjacent Action Discrepancy via Frequency-Selective Filtering for Skeleton-Based Action Segmentation

2026-03-25 · Haoyu Ji, Bowen Chen, Zhihao Yang, Wenze Huang 외 arxiv

Skeleton-based Temporal Action Segmentation (STAS) seeks to densely segment and classify diverse actions within long, untrimmed skeletal motion sequences. However, existing STAS methodologies face challenges of limited i…

Action Segmentation