一作ACL 2026Poster· Natural Language Processing
Long Context Modeling with Ranked Memory-Augmented Retrieval
Ghadir Alselwi · Hao Xue · Shoaib Jameel · Basem Suleiman · Flora D. Salim · Imran Razzak
摘要
Effective long-term memory management is crucial for language models handling extended contexts. We introduce the Enhanced Ranked Memory Augmented Retrieval ERMAR framework, which dynamically ranks memory entries based on relevance. Unlike prior models, ERMAR employs a novel relevance scoring mec...