@inproceedings{liu-etal-2025-david,
title = "{D}avid vs. Goliath: Cost-Efficient Financial {QA} via Cascaded Multi-Agent Reasoning",
author = "Liu, Chenghao and
Liu, Qian and
Zhu, Ziqin and
Fei, Hao and
Mahanti, Aniket",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.225/",
pages = "4212--4229",
ISBN = "979-8-89176-335-7",
abstract = "Large language models (LLMs) have demonstrated remarkable reasoning capabilities, including in financial question answering (FQA). However, the performance in FQA remains limited, particularly in questions that require deep financial knowledge and complex numerical reasoning. While supervised fine-tuning and closed-source LLMs have shown promise, they are often constrained by high costs or computational inefficiency. In this paper, we propose a low-cost yet effective framework, named FinMAN (Financial multi-agent framework), that enables small LLMs (e.g., 8B) to perform complex reasoning tasks without relying on expensive models or task-specific fine-tuning. FinMAN improves formula selection, extraction, and calculation to help small-scale models solve FQA tasks more accurately, with a lightweight verification mechanism to correct common errors. Experimental results show that FinMAN outperforms the best open-source model on BizBench by 10.46{\%} and achieves competitive performance to GPT-3.5 using significantly fewer parameters. Our code and data are publicly available at https://github.com/coenliu/MultiAgentFin."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2025-david">
<titleInfo>
<title>David vs. Goliath: Cost-Efficient Financial QA via Cascaded Multi-Agent Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chenghao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziqin</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Fei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aniket</namePart>
<namePart type="family">Mahanti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Large language models (LLMs) have demonstrated remarkable reasoning capabilities, including in financial question answering (FQA). However, the performance in FQA remains limited, particularly in questions that require deep financial knowledge and complex numerical reasoning. While supervised fine-tuning and closed-source LLMs have shown promise, they are often constrained by high costs or computational inefficiency. In this paper, we propose a low-cost yet effective framework, named FinMAN (Financial multi-agent framework), that enables small LLMs (e.g., 8B) to perform complex reasoning tasks without relying on expensive models or task-specific fine-tuning. FinMAN improves formula selection, extraction, and calculation to help small-scale models solve FQA tasks more accurately, with a lightweight verification mechanism to correct common errors. Experimental results show that FinMAN outperforms the best open-source model on BizBench by 10.46% and achieves competitive performance to GPT-3.5 using significantly fewer parameters. Our code and data are publicly available at https://github.com/coenliu/MultiAgentFin.</abstract>
<identifier type="citekey">liu-etal-2025-david</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.225/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>4212</start>
<end>4229</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T David vs. Goliath: Cost-Efficient Financial QA via Cascaded Multi-Agent Reasoning
%A Liu, Chenghao
%A Liu, Qian
%A Zhu, Ziqin
%A Fei, Hao
%A Mahanti, Aniket
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F liu-etal-2025-david
%X Large language models (LLMs) have demonstrated remarkable reasoning capabilities, including in financial question answering (FQA). However, the performance in FQA remains limited, particularly in questions that require deep financial knowledge and complex numerical reasoning. While supervised fine-tuning and closed-source LLMs have shown promise, they are often constrained by high costs or computational inefficiency. In this paper, we propose a low-cost yet effective framework, named FinMAN (Financial multi-agent framework), that enables small LLMs (e.g., 8B) to perform complex reasoning tasks without relying on expensive models or task-specific fine-tuning. FinMAN improves formula selection, extraction, and calculation to help small-scale models solve FQA tasks more accurately, with a lightweight verification mechanism to correct common errors. Experimental results show that FinMAN outperforms the best open-source model on BizBench by 10.46% and achieves competitive performance to GPT-3.5 using significantly fewer parameters. Our code and data are publicly available at https://github.com/coenliu/MultiAgentFin.
%U https://aclanthology.org/2025.findings-emnlp.225/
%P 4212-4229
Markdown (Informal)
[David vs. Goliath: Cost-Efficient Financial QA via Cascaded Multi-Agent Reasoning](https://aclanthology.org/2025.findings-emnlp.225/) (Liu et al., Findings 2025)
ACL