Long Context Modeling with Ranked Memory-Augmented Retrieval

ACL ARR 2025 February Submission5285 Authors

Abstract: Effective long-term memory management is crucial for language models handling extended contexts. We introduce a novel framework that dynamically ranks memory entries based on relevance. Unlike previous works, our model introduces a novel relevance scoring and a pointwise re-ranking model for key-value embeddings, inspired by learning-to-rank techniques in information retrieval. Enhanced Ranked Memory Augmented Retrieval (ERMAR) achieves state-of-the-art results on standard benchmarks.

Paper Type: Short

Research Area: Language Modeling

Research Area Keywords: retrieval-augmented models, dense retrieval, re-ranking,

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 5285