# Point-in-Time Financial RAG with Frozen LLMs and Market-Feedback Adaptive Retrieval

arXiv: https://arxiv.org/abs/2605.31201 · HTML: https://mlsanity.com/paper/2605.31201/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 5 of its 21 references that are in the map.
- First posted on arXiv 29 May 2026.

## Placed in

- Retrieval-augmented generation / [Legal and financial RAG](https://mlsanity.com/rag/legal-and-financial-rag/)

## Builds on (most cited first, 5 of 5)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [FinAgentBench: A Benchmark Dataset for Agentic Retrieval in Financial Question Answering](https://mlsanity.com/paper/2508.14052/) (2025)
- [Multi-Reranker: Maximizing performance of retrieval-augmented generation in the FinanceRAG challenge](https://mlsanity.com/paper/2411.16732/) (2024)
- [MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering](https://mlsanity.com/paper/2506.20821/) (2025)

## Built on by (most cited first, 2 of 2)

- [Frontier Financial Judgement: Can agents tell what might move a stock?](https://mlsanity.com/paper/2607.20645/) (2026)
- [RICE-Alpha: Reliability-Informed Correction with Event Graphs for LLM-Agent Stock Forecasting](https://mlsanity.com/paper/2609.34004/) (2026)

## Abstract (arXiv)

Financial retrieval-augmented generation (RAG) systems typically rank evidence by textual relevance, but in financial markets evidence utility 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 financial news and SEC filing passages, appends a pre-decision market-context card, and predicts multi-horizon residual-return signals. Our method keeps the LLM frozen and adapts retrieval 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. Supervised LoRA gives modest gains under static retrieval, but after source-memory adaptation, the LoRA reader does not improve over the frozen reader. These results suggest that, for financial RAG systems, learning where to retrieve can be as important as learning how to read, offering a modular route to market-feedback adaptation.