HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling

Documenti analoghi

• Judge Like Human Examiners: A Weighted Importance Multi-Point Evaluation Framework for Generative Tasks with Long-form Answers
  di: Yu, Guoxin, et al.
  Pubblicazione: (2026)
• The Essence of Contextual Understanding in Theory of Mind: A Study on Question Answering with Story Characters
  di: Zhou, Chulun, et al.
  Pubblicazione: (2025)
• THOR-MoE: Hierarchical Task-Guided and Context-Responsive Routing for Neural Machine Translation
  di: Liang, Yunlong, et al.
  Pubblicazione: (2025)
• Figure It Out: Improve the Frontier of Reasoning with Executable Visual States
  di: Chen, Meiqi, et al.
  Pubblicazione: (2025)
• PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts
  di: Yu, Mo, et al.
  Pubblicazione: (2025)