@inproceedings{yang-etal-2026-analysisbank,
title = "{A}nalysis{B}ank: An Expert Analysis Pattern Library for Financial Report Generation",
author = "Yang, Yajing and
Ma, Yunshan and
Koa, Kelvin J.L. and
Kan, Min-Yen",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.994/",
pages = "22870--22892",
ISBN = "979-8-89176-459-0",
abstract = "We argue that financial report generation should operate at the analytical rather than structural level, composing content from data-derived insights rather than high-level topics or sections. To this end, we propose AnalysisBank, which distills expert reports into a reusable library of *Analyses*, each pairing a data signal, an analytical move, and the expert span it was derived from. At inference time, AnalysisBank matches input signals to library entries and applies the retrieved moves to compose the report. A study of *Analyses* distilled from 550 expert reports reveals a heavy-tailed distribution of 47{--}52 signal types spanning 13 move types. On two financial benchmarks across four LLM backbones, AnalysisBank increases the proportion of novel, data-grounded insights by 1.7{--}3.7{\texttimes} over structural-level baselines. Transfer to scientific writing suggests that the distinction generalizes beyond finance. Code and the distilled *Analysis* library are available at [https://github.com/yajingyang/AnalysisBank](https://github.com/yajingyang/AnalysisBank)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-analysisbank">
<titleInfo>
<title>AnalysisBank: An Expert Analysis Pattern Library for Financial Report Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yajing</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunshan</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kelvin</namePart>
<namePart type="given">J.L.</namePart>
<namePart type="family">Koa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</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</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>We argue that financial report generation should operate at the analytical rather than structural level, composing content from data-derived insights rather than high-level topics or sections. To this end, we propose AnalysisBank, which distills expert reports into a reusable library of *Analyses*, each pairing a data signal, an analytical move, and the expert span it was derived from. At inference time, AnalysisBank matches input signals to library entries and applies the retrieved moves to compose the report. A study of *Analyses* distilled from 550 expert reports reveals a heavy-tailed distribution of 47–52 signal types spanning 13 move types. On two financial benchmarks across four LLM backbones, AnalysisBank increases the proportion of novel, data-grounded insights by 1.7–3.7× over structural-level baselines. Transfer to scientific writing suggests that the distinction generalizes beyond finance. Code and the distilled *Analysis* library are available at [https://github.com/yajingyang/AnalysisBank](https://github.com/yajingyang/AnalysisBank).</abstract>
<identifier type="citekey">yang-etal-2026-analysisbank</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.994/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>22870</start>
<end>22892</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AnalysisBank: An Expert Analysis Pattern Library for Financial Report Generation
%A Yang, Yajing
%A Ma, Yunshan
%A Koa, Kelvin J.L.
%A Kan, Min-Yen
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F yang-etal-2026-analysisbank
%X We argue that financial report generation should operate at the analytical rather than structural level, composing content from data-derived insights rather than high-level topics or sections. To this end, we propose AnalysisBank, which distills expert reports into a reusable library of *Analyses*, each pairing a data signal, an analytical move, and the expert span it was derived from. At inference time, AnalysisBank matches input signals to library entries and applies the retrieved moves to compose the report. A study of *Analyses* distilled from 550 expert reports reveals a heavy-tailed distribution of 47–52 signal types spanning 13 move types. On two financial benchmarks across four LLM backbones, AnalysisBank increases the proportion of novel, data-grounded insights by 1.7–3.7× over structural-level baselines. Transfer to scientific writing suggests that the distinction generalizes beyond finance. Code and the distilled *Analysis* library are available at [https://github.com/yajingyang/AnalysisBank](https://github.com/yajingyang/AnalysisBank).
%U https://aclanthology.org/2026.emnlp-main.994/
%P 22870-22892
Markdown (Informal)
[AnalysisBank: An Expert Analysis Pattern Library for Financial Report Generation](https://aclanthology.org/2026.emnlp-main.994/) (Yang et al., EMNLP 2026)
ACL