Long Context Modeling with Ranked Memory-Augmented Retrieval

• URL: http://arxiv.org/abs/2503.14800v1
• Date: Wed, 19 Mar 2025 00:24:01 GMT
• Title: Long Context Modeling with Ranked Memory-Augmented Retrieval
• Authors: Ghadir Alselwi, Hao Xue, Shoaib Jameel, Basem Suleiman, Flora D. Salim, Imran Razzak,
• Abstract summary: We introduce a novel framework that dynamically ranks memory entries based on relevance.<n>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.
• Score: 18.4248685578126
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Quantifying Memory Utilization with Effective State-Size [73.52115209375343]
  We develop a measure of textitmemory utilization' This metric is tailored to the fundamental class of systems with textitinput-invariant and textitinput-varying linear operators
  arXiv  Detail & Related papers  (2025-04-28T08:12:30Z)
• Beyond Content Relevance: Evaluating Instruction Following in Retrieval Models [25.301280441283147]
  This study evaluates the instruction-following capabilities of various retrieval models beyond content relevance.<n>We develop a novel retrieval evaluation benchmark spanning six document-level attributes.<n>Our findings indicate that although fine-tuning models on instruction-aware retrieval datasets enhance performance, most models still fall short of instruction compliance.
  arXiv  Detail & Related papers  (2024-10-31T11:47:21Z)
• Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning [64.93848182403116]
  Current deep-learning memory models struggle in reinforcement learning environments that are partially observable and long-term. We introduce the Stable Hadamard Memory, a novel memory model for reinforcement learning agents. Our approach significantly outperforms state-of-the-art memory-based methods on challenging partially observable benchmarks.
  arXiv  Detail & Related papers  (2024-10-14T03:50:17Z)
• MEMORYLLM: Towards Self-Updatable Large Language Models [101.3777486749529]
  Existing Large Language Models (LLMs) usually remain static after deployment. We introduce MEMORYLLM, a model that comprises a transformer and a fixed-size memory pool. MEMORYLLM can self-update with text knowledge and memorize the knowledge injected earlier.
  arXiv  Detail & Related papers  (2024-02-07T07:14:11Z)
• History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling [28.27368343751272]
  We propose a History Semantic Graph Enhanced KBQA model (HSGE) that is able to effectively model long-range semantic dependencies in conversation history. We evaluate HSGE on a widely used benchmark dataset for complex sequential question answering.
  arXiv  Detail & Related papers  (2023-06-12T05:10:58Z)
• A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning [56.450090618578]
  Class-Incremental Learning (CIL) aims to train a model with limited memory size to meet this requirement. We show that when counting the model size into the total budget and comparing methods with aligned memory size, saving models do not consistently work. We propose a simple yet effective baseline, denoted as MEMO for Memory-efficient Expandable MOdel.
  arXiv  Detail & Related papers  (2022-05-26T08:24:01Z)
• Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form Stories [21.99104738567138]
  This paper takes a recent unsupervised method for salience detection derived from Barthes Cardinal Functions and theories of surprise. We improve the standard transformer language model by incorporating an external knowledgebase and adding a memory mechanism. Our evaluation against this data demonstrates that our salience detection model improves performance over and above a non-knowledgebase and memory augmented language model.
  arXiv  Detail & Related papers  (2021-09-08T16:15:50Z)
• Memory-Based Semantic Parsing [79.48882899104997]
  We present a memory-based model for context-dependent semantic parsing. We learn a context memory controller that manages the memory by maintaining the cumulative meaning of sequential user utterances.
  arXiv  Detail & Related papers  (2021-09-07T16:15:13Z)
• Learning to Learn Variational Semantic Memory [132.39737669936125]
  We introduce variational semantic memory into meta-learning to acquire long-term knowledge for few-shot learning. The semantic memory is grown from scratch and gradually consolidated by absorbing information from tasks it experiences. We formulate memory recall as the variational inference of a latent memory variable from addressed contents.
  arXiv  Detail & Related papers  (2020-10-20T15:05:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.