<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-welsch-2026-point">
    <titleInfo>
        <title>Point-in-Time Financial RAG with Frozen LLM Readers and Market-Feedback Adaptive Retrieval</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zijie</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Roy</namePart>
        <namePart type="given">E</namePart>
        <namePart type="family">Welsch</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Pepa</namePart>
            <namePart type="family">Atanasova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gholamreza</namePart>
            <namePart type="family">Haffari</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Minghan</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-460-6</identifier>
    </relatedItem>
    <abstract>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 reader frozen and adapts retrieval through an external Bayesian source memory updated from matured residual-return feedback. On a fixed 89-stock FNSPID universe with point-in-time EDGAR evidence, 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.</abstract>
    <identifier type="citekey">zhao-welsch-2026-point</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-industry.186/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>3137</start>
            <end>3148</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Point-in-Time Financial RAG with Frozen LLM Readers and Market-Feedback Adaptive Retrieval
%A Zhao, Zijie
%A Welsch, Roy E.
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F zhao-welsch-2026-point
%X 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 reader frozen and adapts retrieval through an external Bayesian source memory updated from matured residual-return feedback. On a fixed 89-stock FNSPID universe with point-in-time EDGAR evidence, 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.
%U https://aclanthology.org/2026.emnlp-industry.186/
%P 3137-3148

Markdown (Informal)

[Point-in-Time Financial RAG with Frozen LLM Readers and Market-Feedback Adaptive Retrieval](https://aclanthology.org/2026.emnlp-industry.186/) (Zhao & Welsch, EMNLP 2026)

• Point-in-Time Financial RAG with Frozen LLM Readers and Market-Feedback Adaptive Retrieval (Zhao & Welsch, EMNLP 2026)

ACL

• Zijie Zhao and Roy E. Welsch. 2026. Point-in-Time Financial RAG with Frozen LLM Readers and Market-Feedback Adaptive Retrieval. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 3137–3148, Budapest, Hungary. Association for Computational Linguistics.