<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="swami-pandey-2026-spendsight">
    <titleInfo>
        <title>SpendSight: Privacy-Preserving Personal Finance Q&amp;A with Sub-2B LLMs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sajag</namePart>
        <namePart type="family">Swami</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yash</namePart>
        <namePart type="family">Pandey</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 11th Workshop on Financial Technology and Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jimin</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yongjae</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sophia</namePart>
            <namePart type="family">Ananiadou</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hsin-Hsi</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hiroya</namePart>
            <namePart type="family">Takamura</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Chung-Chi</namePart>
            <namePart type="family">Chen</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">979-8-89176-466-8</identifier>
    </relatedItem>
    <abstract>People often speculate about their personal finances: *”Has my spending on groceries increased compared to past year?”*, *”How does my spending on clothes look for the past 6 months?”*. However, answering them with cloud-hosted LLMs transmits sensitive financial data to external servers, exposing users to data leakage and inferential privacy risks. We present **SpendSight**, a study of fully on-device personal finance Q A tool calling that keeps all data strictly local. We evaluate seven quantized models (six sub-2B and one 3B) across 115 test cases and five analytical tools, comparing single-agent against dual-agent (router-specialist) architectures. Dual-agent decomposition yields the largest time gains for the Qwen3.5 family. **Qwen3.5-0.8B** achieves **61.7% Correct Ratio** (**89.1% Task Accuracy**) in **3.0 s** with **1.2 GB RAM** in dual-agent mode. A 3B reference model (**G9v3-3B**, Q4_K_M) achieves **71.7% Correct Ratio** (**90.6% Task Accuracy**) at **2.3 s** in single agent mode, suggesting that larger models with aggressive quantization can bypass decomposition.</abstract>
    <identifier type="citekey">swami-pandey-2026-spendsight</identifier>
    <location>
        <url>https://aclanthology.org/2026.finnlp-1.14/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>153</start>
            <end>179</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SpendSight: Privacy-Preserving Personal Finance Q&A with Sub-2B LLMs
%A Swami, Sajag
%A Pandey, Yash
%Y Huang, Jimin
%Y Lee, Yongjae
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%Y Takamura, Hiroya
%Y Chen, Chung-Chi
%S Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-466-8
%F swami-pandey-2026-spendsight
%X People often speculate about their personal finances: *”Has my spending on groceries increased compared to past year?”*, *”How does my spending on clothes look for the past 6 months?”*. However, answering them with cloud-hosted LLMs transmits sensitive financial data to external servers, exposing users to data leakage and inferential privacy risks. We present **SpendSight**, a study of fully on-device personal finance Q A tool calling that keeps all data strictly local. We evaluate seven quantized models (six sub-2B and one 3B) across 115 test cases and five analytical tools, comparing single-agent against dual-agent (router-specialist) architectures. Dual-agent decomposition yields the largest time gains for the Qwen3.5 family. **Qwen3.5-0.8B** achieves **61.7% Correct Ratio** (**89.1% Task Accuracy**) in **3.0 s** with **1.2 GB RAM** in dual-agent mode. A 3B reference model (**G9v3-3B**, Q4_K_M) achieves **71.7% Correct Ratio** (**90.6% Task Accuracy**) at **2.3 s** in single agent mode, suggesting that larger models with aggressive quantization can bypass decomposition.
%U https://aclanthology.org/2026.finnlp-1.14/
%P 153-179

Markdown (Informal)

[SpendSight: Privacy-Preserving Personal Finance Q&A with Sub-2B LLMs](https://aclanthology.org/2026.finnlp-1.14/) (Swami & Pandey, FinNLP 2026)

• SpendSight: Privacy-Preserving Personal Finance Q&A with Sub-2B LLMs (Swami & Pandey, FinNLP 2026)

ACL

• Sajag Swami and Yash Pandey. 2026. SpendSight: Privacy-Preserving Personal Finance Q&A with Sub-2B LLMs. In Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing, pages 153–179, Budapest, Hungary. Association for Computational Linguistics.