X-GORB Scholar Search

搜索建议
网页 图片 音乐 学术 词典
时间范围: 全部时间 最近1天 最近1周 最近1月 最近1年
找到约 0 个学术文献结果（用时 ） 时间范围: 最近1天
Favicon of arxiv.org
arxiv.org
http://arxiv.org > abs > 2608.05576v2
Where Models Converge and Humans Diverge: A Coverage Framework for Distributional Pluralism in Open-Ended Generation
Favicon of arxiv.org
arxiv.org
http://arxiv.org > abs > 2606.13873v1
Natively Unlearnable Large Language Models
Favicon of arxiv.org
arxiv.org
http://arxiv.org > abs > 2602.12108v1
The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context
Favicon of arxiv.org
arxiv.org
http://arxiv.org > abs > 2601.04278v2
From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning
Favicon of arxiv.org
arxiv.org
http://arxiv.org > abs > 2601.02671v1
Extracting books from production language models
Favicon of arxiv.org
arxiv.org
http://arxiv.org > abs > 2510.25732v2
What the "Spotless" Mind Remembers: How Knowledge Entanglement Shapes What Leaks After Unlearning in LLMs
Favicon of arxiv.org
arxiv.org
http://arxiv.org > abs > 2510.22376v1
Label Smoothing Improves Gradient Ascent in LLM Unlearning
Favicon of arxiv.org
arxiv.org
http://arxiv.org > abs > 2510.18201v1
MARCUS: An Event-Centric NLP Pipeline that generates Character Arcs from Narratives
Favicon of arxiv.org
arxiv.org
http://arxiv.org > abs > 2508.21770v2
What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos
Favicon of arxiv.org
arxiv.org
http://arxiv.org > abs > 2508.06595v3
LLM Unlearning Without an Expert Curated Dataset