paper-with-me

홈 › Papers

ScEdit: Script-based Assessment of Knowledge Editing

2025-05-29 · Xinye Li, Zunwen Zheng, Qian Zhang, Dekai Zhuang, Jiabao Kang, Liyan Xu, Qingbin Liu, Xi Chen, Zhiying Tu, Dianhui Chu, Dianbo Sui

Knowledge Editing (KE) has gained increasing attention, yet current KE tasks remain relatively simple. Under current evaluation frameworks, many editing methods achieve exceptionally high scores, sometimes nearing perfection. However, few studies integrate KE into real-world application scenarios (e.g., recent interest in LLM-as-agent). To support our analysis, we introduce a novel script-based benchmark -- ScEdit (Script-based Knowledge Editing Benchmark) -- which encompasses both counterfactual and temporal edits. We integrate token-level and text-level evaluation methods, comprehensively analyzing existing KE techniques. The benchmark extends traditional fact-based ("What"-type question) evaluation to action-based ("How"-type question) evaluation. We observe that all KE methods exhibit a drop in performance on established metrics and face challenges on text-level metrics, indicating a challenging task. Our benchmark is available at https://github.com/asdfo123/ScEdit.

📄 PDF Abstract BibTeX arXiv:2505.23291

Code (1)

asdfo123/scedit 공식 구현

Tasks

counterfactualknowledge editing

Similar Papers 제목 키워드 기반

SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing

2023-12-18 · CVPR 2024 1 · Zeyinzi Jiang, Chaojie Mao, Yulin Pan, Zhen Han 외

Image diffusion models have been utilized in various tasks, such as text-to-image generation and controllable image synthesis. Recent research has introduced tuning methods that make subtle adjustments to the original mo…

DecoderImage GenerationText to Image GenerationText-to-Image Generation

History Matters: Temporal Knowledge Editing in Large Language Model

2023-12-09 · Xunjian Yin, Jin Jiang, Liming Yang, Xiaojun Wan

The imperative task of revising or updating the knowledge stored within large language models arises from two distinct sources: intrinsic errors inherent in the model which should be corrected and outdated knowledge due …

knowledge editingLanguage ModelingLanguage ModellingLarge Language Model+1

Pioneering Reliable Assessment in Text-to-Image Knowledge Editing: Leveraging a Fine-Grained Dataset and an Innovative Criterion

2024-09-26 · Hengrui Gu, Kaixiong Zhou, Yili Wang, Ruobing Wang 외

During pre-training, the Text-to-Image (T2I) diffusion models encode factual knowledge into their parameters. These parameterized facts enable realistic image generation, but they may become obsolete over time, thereby m…

Image GenerationIn-Context Learningknowledge editingWorld Knowledge

VE-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment

2024-08-21 · Shangkun Sun, Xiaoyu Liang, Songlin Fan, Wenxu Gao 외

Text-driven video editing has recently experienced rapid development. Despite this, evaluating edited videos remains a considerable challenge. Current metrics tend to fail to align with human perceptions, and effective q…

Video AlignmentVideo EditingVideo Quality AssessmentVisual Question Answering (VQA)

Stable Knowledge Editing in Large Language Models

2024-02-20 · Zihao Wei, Liang Pang, Hanxing Ding, Jingcheng Deng 외

Efficient knowledge editing of large language models is crucial for replacing obsolete information or incorporating specialized knowledge on a large scale. However, previous methods implicitly assume that knowledge is lo…

knowledge editing