Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models

  • 类型:arxiv
  • 标识:2607.19604
  • 链接:https://arxiv.org/abs/2607.19604
  • 主分类:llm-infra
  • 形态:method
  • 被引:0
  • 被引来源:Semantic Scholar + OpenAlex
  • S2被引:0
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:The design decouples the hypernetwork's injection capacity from the target model's general capability, enabling, for the first time, a rigorous study of scaling laws for hypernetwork architectures, and provides the first empirically grounded scaling laws to guide hypernetworks for factual reasoning in large language models.
  • OpenAlex ID:W7170162330
  • OpenAlex DOI:10.48550/arxiv.2607.19604
  • DOI:10.48550/arxiv.2607.19604
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2607.19604
  • OpenAlex更新:2026-08-24
  • 待LLM分类:否
  • 成熟度:research
  • 场景:knowledge injection、hypernetworks、scaling laws
  • 标题中文:基于超网络知识注入的大语言模型 Scaling Laws
  • TLDR中文:该设计将 hypernetwork 的注入能力与目标模型的通用能力解耦,首次实现了对 hypernetwork 架构 scaling law 的严格研究,并提供了首个基于实证的 scaling law,用以指导大语言模型中面向事实推理的 hypernetwork 设计。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-23-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-07-24-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]