Saved in:
Bibliographic Details
Main Authors: Zhao, Zijie, Welsch, Roy E.
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.31201
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911732024213504
author Zhao, Zijie
Welsch, Roy E.
author_facet Zhao, Zijie
Welsch, Roy E.
contents Financial retrieval-augmented generation (RAG) systems typically rank evidence by textual relevance, but in financial markets the useful evidence source depends on event type, forecast horizon, and market context. We study news-triggered event-impact prediction as a point-in-time financial RAG problem. For each company-news anchor, the system retrieves related financial news and SEC filing passages, appends a pre-decision market-context card, and predicts multi-horizon residual-return signals. Our method keeps the large language model (LLM) reader frozen and adapts the retrieval layer through an external Bayesian source memory updated from matured residual-return feedback. On a fixed 89-stock Nasdaq-oriented universe derived from the FinRL-DeepSeek/FNSPID task, using original FNSPID news and point-in-time EDGAR filing passages, Frozen Reader with Source Memory improves held-out macro-F1 from 0.438 to 0.471 and downstream portfolio Sharpe from 0.52 to 0.84 relative to Frozen Reader with No Memory. A supervised LoRA reader improves static RAG modestly, but does not improve over the frozen source-memory reader. These results suggest that, for financial RAG, learning where to retrieve from can be as important as learning how to read, offering a simple, modular route to market-feedback adaptation.
format Preprint
id arxiv_https___arxiv_org_abs_2605_31201
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning Whom to Trust: Market-Feedback Adaptive Retrieval for Frozen LLMs in Event-Driven Financial RAG
Zhao, Zijie
Welsch, Roy E.
Computation and Language
Financial retrieval-augmented generation (RAG) systems typically rank evidence by textual relevance, but in financial markets the useful evidence source depends on event type, forecast horizon, and market context. We study news-triggered event-impact prediction as a point-in-time financial RAG problem. For each company-news anchor, the system retrieves related financial news and SEC filing passages, appends a pre-decision market-context card, and predicts multi-horizon residual-return signals. Our method keeps the large language model (LLM) reader frozen and adapts the retrieval layer through an external Bayesian source memory updated from matured residual-return feedback. On a fixed 89-stock Nasdaq-oriented universe derived from the FinRL-DeepSeek/FNSPID task, using original FNSPID news and point-in-time EDGAR filing passages, Frozen Reader with Source Memory improves held-out macro-F1 from 0.438 to 0.471 and downstream portfolio Sharpe from 0.52 to 0.84 relative to Frozen Reader with No Memory. A supervised LoRA reader improves static RAG modestly, but does not improve over the frozen source-memory reader. These results suggest that, for financial RAG, learning where to retrieve from can be as important as learning how to read, offering a simple, modular route to market-feedback adaptation.
title Learning Whom to Trust: Market-Feedback Adaptive Retrieval for Frozen LLMs in Event-Driven Financial RAG
topic Computation and Language
url https://arxiv.org/abs/2605.31201