paper-with-me

홈 › Papers

Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language Models

2024-06-03 · Cheng-Hsun Hsueh, Paul Kuo-Ming Huang, Tzu-Han Lin, Che-Wei Liao, Hung-Chieh Fang, Chao-Wei Huang, Yun-Nung Chen

Knowledge editing is a rising technique for efficiently updating factual knowledge in large language models (LLMs) with minimal alteration of parameters. However, recent studies have identified side effects, such as knowledge distortion and the deterioration of general abilities, that have emerged after editing. Despite these findings, evaluating the pitfalls of knowledge editing often relies on inconsistent metrics and benchmarks, lacking a uniform standard. In response, this survey presents a comprehensive study of these side effects, providing a unified perspective on the challenges of knowledge editing in LLMs by conducting experiments with consistent metrics and benchmarks. Additionally, we review related works and outline potential research directions to address these limitations. Our survey highlights the limitations of current knowledge editing methods, emphasizing the need for a deeper understanding of the inner knowledge structures of LLMs and improved knowledge editing methods. To foster future research, we have released the complementary materials publicly in https://github.com/MiuLab/EditLLM-Survey.

📄 PDF Abstract BibTeX arXiv:2406.01436

Code (1)

miulab/editllm-survey 공식 구현

Tasks

knowledge editingSurvey

Similar Papers 제목 키워드 기반

Unveiling the Pitfalls of Knowledge Editing for Large Language Models

2023-10-03 · Zhoubo Li, Ningyu Zhang, Yunzhi Yao, Mengru Wang 외

As the cost associated with fine-tuning Large Language Models (LLMs) continues to rise, recent research efforts have pivoted towards developing methodologies to edit implicit knowledge embedded within LLMs. Yet, there's …

knowledge editing

Exploration and Improvement of Nerf-based 3D Scene Editing Techniques

2024-01-23 · Shun Fang, Ming Cui, Xing Feng, Yanan Zhang

NeRF's high-quality scene synthesis capability was quickly accepted by scholars in the years after it was proposed, and significant progress has been made in 3D scene representation and synthesis. However, the high compu…

3D scene EditingNeRF

MindBridge: Scalable and Cross-Model Knowledge Editing via Memory-Augmented Modality

2025-03-04 · Shuaike Li, Kai Zhang, Qi Liu, Enhong Chen

Knowledge editing is a technique for efficiently and accurately updating the knowledge of large language models (LLMs) to alleviate obsolescence and correct errors. However, most existing methods overfit to specific mode…

knowledge editing

MindEdit-Bench: Benchmarking Object-Level Counterfactual Spatial Reasoning in VLMs from In-the-Wild Photos

2026-07-01 · Leyuan Yu, Xiao Tang, Minghao Liu, Xinyuan Li 외 arxiv

Benchmarks for vision-language models (VLMs) mostly test observational spatial reasoning: models describe relations already visible in the input. Existing what-if tasks typically vary the observer while keeping the scene…

Spatial Reasoning

MindAU: EEG-Conditioned Facial Action Unit Editing via Dual-Stream Manifold Alignment

2026-07-01 · Zhenhang Li, Xin Zhou, Hao Deng, Lijun Yin arxiv

Recent brain decoding studies have made substantial progress in reconstructing externally perceived visual content from neural signals. However, using electroencephalography (EEG) recordings to guide facial expression ed…

Brain DecodingImage Editing