paper-with-me

knowledge editing

1개 벤치마크 · 논문 288편 · 이 태스크의 논문 보기 →

Benchmarks

zsRE

결과 16개

Most implemented

Papers

KLOD: Locality-Preserving Knowledge Editing via Non-Target Distribution Preservation

2026-08-28 · Hojun Jeong, Gyunyeop Kim, Sangwoo Kang arxiv

Fine-tuning-based knowledge editing is simple and architecture-agnostic, but standard cross-entropy increases the edited target probability without explicitly constraining changes in the non-target output distribution. I…

knowledge editing

PersonaEdit: Representative Sample Selection for Personalized Model Editing

2026-08-28 · You-Mei Huang, Chung-Chi Chen, An-Zi Yen arxiv

Personalization has attracted growing interest in LLM applications, yet existing retrieval-based approaches depend heavily on retrieval quality and degrade in long-term interactions. Model editing, which directly modifie…

knowledge editing

Leveraging Association Context Retrieval in Knowledge Edit- ing to Build White-Box Attacks on LLMs

2026-08-18 · Roman Maksimov, Vladimir Aletov, Vladimir Solodkin, Dmitry Bylinkin 외 arxiv

As large language models (LLMs) are granted increasing autonomy, it is essential to investigate methods that can induce unsafe behavior. We propose a novel white-box attack inspired by locate-then-edit approaches from th…

knowledge editing

Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing

2026-08-12 · Tianci Liu, Zihan Dong, Tianchun Li, Yi-Chung Chen 외 hf

Large language models (LLMs) achieve remarkable performance across natural language tasks, yet they are trained on static corpora and their knowledge quickly becomes outdated in a fast-changing world. This motivates know…

knowledge editing

ForgetBench: Benchmarking Forgetting Dynamics of Long-Term Parametric Memory in Language Models

2026-07-29 · Ruxi Gu, Zhenliang Zhang, Wei Wang arxiv

Large language models (LLMs) have demonstrated strong capabilities in knowledge acquisition and reasoning, yet their ability to retain previously acquired knowledge under repeated updates remains insufficiently understoo…

knowledge editing

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs

2026-07-12 · Shrestha Datta, Hongfu Liu, Anshuman Chhabra arxiv

Understanding which parameters are influential in Large Language Models (LLMs) is central to improving their efficiency, reliability, and interpretability. We introduce Weight-Adjusted Gradients (WAG), a simple yet effec…

knowledge editing

전체 288편 보기 →