Tag: Embeddings

All the articles with the tag "Embeddings".

• HINT: Hypernetwork Approach to Training Weight Interval Regions in Continual Learning

  Published: 13 May, 2025 |  at  11:21 AM

  

  65.63 🤔

  HINT proposes a continual learning framework using interval arithmetic in embedding space with a hypernetwork to generate target network weights, achieving improved scalability and non-forgetting guarantees over InterContiNet while outperforming several benchmarks, though struggling with complex datasets.

• HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization

  Published: 4 May, 2025 |  at  04:33 PM

  

  62.92 🤔

  本文提出基于超网络的HYPEROFA方法，用于初始化新语言令牌嵌入，提高PLM对低资源语言的适应性，性能优于随机初始化并与OFA方法持平或更好。

• ASIDE: Architectural Separation of Instructions and Data in Language Models

  Published: 4 May, 2025 |  at  04:27 PM

  

  53.34 🤔

  本文提出ASIDE方法，通过在嵌入级别应用固定正交旋转实现大型语言模型的指令-数据架构分离，提高了模型的安全性和对提示注入攻击的鲁棒性，同时不牺牲性能。