# MeVe: A Modular System for Memory Verification and Effective Context Control in Language Models

arXiv: https://arxiv.org/abs/2509.01514 · HTML: https://mlsanity.com/paper/2509.01514/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 15 of its 32 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 15 of 15)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (2023)
- [The Power of Noise: Redefining Retrieval for RAG Systems](https://mlsanity.com/paper/2401.14887/) (2024)
- [A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models](https://mlsanity.com/paper/2401.01313/) (2024)
- [Token-Budget-Aware LLM Reasoning](https://mlsanity.com/paper/2412.18547/) (2024)
- [Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models](https://mlsanity.com/paper/2402.02244/) (2024)
- [The Distracting Effect: Understanding Irrelevant Passages in RAG](https://mlsanity.com/paper/2505.06914/) (2025)
- [More Documents, Same Length: Isolating the Challenge of Multiple Documents in RAG](https://mlsanity.com/paper/2503.04388/) (2025)
- [KaPQA: Knowledge-Augmented Product Question-Answering](https://mlsanity.com/paper/2407.16073/) (2024)
- [Modular Retrieval for Generalization and Interpretation](https://mlsanity.com/paper/2303.13419/) (2023)

## Built on by (most cited first, 1 of 1)

- [Resource Consumption Threats in Large Language Models](https://mlsanity.com/paper/2603.16068/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) systems typically face constraints because of their inherent mechanism: a simple top-k semantic search [1]. The approach often leads to the incorporation of irrelevant or redundant information in the context, degrading performance and efficiency [10][11]. This paper presents MeVe, a novel modular architecture intended for Memory Verification and smart context composition. MeVe rethinks the RAG paradigm by proposing a five-phase modular design that distinctly breaks down the retrieval and context composition process into distinct, auditable, and independently tunable phases: initial retrieval, relevance verification, fallback retrieval, context prioritization, and token budgeting. This architecture enables fine-grained control of what knowledge is made available to an LLM, enabling task-dependent filtering and adaptation. We release a reference implementation of MeVe as a proof of concept and evaluate its performance on knowledge-heavy QA tasks over a subset of English Wikipedia [22]. Our results demonstrate that by actively verifying information before composition, MeVe significantly improves context efficiency, achieving a 57% reduction on the Wikipedia dataset and a 75% reduction on the more complex HotpotQA dataset compared to standard RAG implementations [25]. This work provides a framework for more scalable and reliable LLM applications. By refining and distilling contextual information, MeVe offers a path toward better grounding and more accurate factual support [16].