Cover Image

Architecture Matters More Than Scale: A Comparative Study of Retrieval and Memory Augmentation for Financial QA Under SME Compute Constraints

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Jianan, Yang, Jing, Li, Xianyou, Yan, Weiran, Wu, Yichao, Liang, Penghao, Yuan, Mengwei
Format:	Preprint
Published:	2026
Subjects:	Information Retrieval I.2.7; H.3.3
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TA-Mem: Tool-Augmented Autonomous Memory Retrieval for LLM in Long-Term Conversational QA
by: Yuan, Mengwei, et al.
Published: (2026)

Storage Is Not Memory: A Retrieval-Centered Architecture for Agent Recall
by: Adler, Joshua, et al.
Published: (2026)

Query-Centric Graph Retrieval Augmented Generation
by: Wu, Yaxiong, et al.
Published: (2025)

Numbers Matter! Bringing Quantity-awareness to Retrieval Systems
by: Almasian, Satya, et al.
Published: (2024)

Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph Walks
by: Böckling, Martin, et al.
Published: (2025)

MLDocRAG: Multimodal Long-Context Document Retrieval Augmented Generation
by: Zhang, Yongyue, et al.
Published: (2026)

Prompt Perturbation in Retrieval-Augmented Generation based Large Language Models
by: Hu, Zhibo, et al.
Published: (2024)

BridgeRAG: Training-Free Bridge-Conditioned Retrieval for Multi-Hop Question Answering
by: Bacellar, Andre
Published: (2026)

Scaling Multilingual Semantic Search in Uber Eats Delivery
by: Ling, Bo, et al.
Published: (2026)

Exploring Information Retrieval Landscapes: An Investigation of a Novel Evaluation Techniques and Comparative Document Splitting Methods
by: Narimissa, Esmaeil, et al.
Published: (2024)

The Reasoning Bottleneck in Graph-RAG: Structured Prompting and Context Compression for Multi-Hop QA
by: Zarrinkia, Yasaman, et al.
Published: (2026)

AuthorityBench: Benchmarking LLM Authority Perception for Reliable Retrieval-Augmented Generation
by: Yao, Zhihui, et al.
Published: (2026)

MasterSet: A Large-Scale Benchmark for Must-Cite Citation Recommendation in the AI/ML Literature
by: Ratul, Md Toyaha Rahman, et al.
Published: (2026)

CLAP: Coreference-Linked Augmentation for Passage Retrieval
by: Xu, Huanwei, et al.
Published: (2025)

Benchmarking Retrieval Strategies for Biomedical Retrieval-Augmented Generation: A Controlled Empirical Study
by: Bal, Devi Prasad, et al.
Published: (2026)

Prompt-RAG: Pioneering Vector Embedding-Free Retrieval-Augmented Generation in Niche Domains, Exemplified by Korean Medicine
by: Kang, Bongsu, et al.
Published: (2024)

Local Hybrid Retrieval-Augmented Document QA
by: Astrino, Paolo
Published: (2025)

Less LLM, More Documents: Searching for Improved RAG
by: Ning, Jingjie, et al.
Published: (2025)

CUE-R: Beyond the Final Answer in Retrieval-Augmented Generation
by: Jain, Siddharth, et al.
Published: (2026)

Entity-Collision: A Stratified Protocol for Attributing Retrieval Lift in Agent Memory
by: Deng, Youwang
Published: (2026)

Controllable Evidence Selection in Retrieval-Augmented Question Answering via Deterministic Utility Gating
by: Unda, Victor P.
Published: (2026)

Augmented Relevance Datasets with Fine-Tuned Small LLMs
by: Fitte-Rey, Quentin, et al.
Published: (2025)

FinBERT-QA: Financial Question Answering with pre-trained BERT Language Models
by: Yuan, Bithiah
Published: (2025)

SGMem: Sentence Graph Memory for Long-Term Conversational Agents
by: Wu, Yaxiong, et al.
Published: (2025)

RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets
by: Kartal, Muhammed Yusuf, et al.
Published: (2025)

Peeling Back the Layers: An In-Depth Evaluation of Encoder Architectures in Neural News Recommenders
by: Iana, Andreea, et al.
Published: (2024)

Expanding Relevance Judgments for Medical Case-based Retrieval Task with Multimodal LLMs
by: Pires, Catarina, et al.
Published: (2025)

Inference-Free Multimodal Learned Sparse Retrieval for Production-Scale Visual Document Search
by: Cho, Gyu-Hwung, et al.
Published: (2026)

Harnessing multiple LLMs for Information Retrieval: A case study on Deep Learning methodologies in Biodiversity publications
by: Kommineni, Vamsi Krishna, et al.
Published: (2024)

MeVer at CheckThat! 2026: Cluster-Aware Hard-Negative Mining for Multilingual Scientific-Source Retrieval
by: Bakagianni, Juli, et al.
Published: (2026)

Temporal Leakage in Search-Engine Date-Filtered Web Retrieval: A Retrospective Forecasting Case Study
by: Lahib, Ali El, et al.
Published: (2026)

A Systematic Framework for Enterprise Knowledge Retrieval: Leveraging LLM-Generated Metadata to Enhance RAG Systems
by: Mishra, Pranav Pushkar, et al.
Published: (2025)

Career-Aware Resume Tailoring via Multi-Source Retrieval-Augmented Generation with Provenance Tracking: A Case Study
by: Abhinav, Kumar
Published: (2026)

Train Once, Use Flexibly: A Modular Framework for Multi-Aspect Neural News Recommendation
by: Iana, Andreea, et al.
Published: (2023)

Session Context Embedding for Intent Understanding in Product Search
by: Mehrdad, Navid, et al.
Published: (2024)

Does UMBRELA Work on Other LLMs?
by: Farzi, Naghmeh, et al.
Published: (2025)

Algorithmic Trust and Compliance: Benchmarking Brand Notability for UK iGaming Entities in Generative Search Engines
by: Oruesagasti, Julen
Published: (2026)

Criteria-Based LLM Relevance Judgments
by: Farzi, Naghmeh, et al.
Published: (2025)

Intent-Driven Dynamic Chunking: Segmenting Documents to Reflect Predicted Information Needs
by: Koutsiaris, Christos
Published: (2026)

Graph-GRPO: Dependency-Aware Credit Assignment for Generative E-commerce Search Relevance
by: Che, Jiarui, et al.
Published: (2026)