@inproceedings{atiq-butt-2026-ahsanblah,
title = "{A}hsan{BLAH} at the {F}in{E}val 2026: Grounded Two-Stage Financial {QA} with {LLM}-Judge Verification",
author = "Atiq, Muhammad Ahsan and
Butt, Mohib Ahmad",
editor = "Huang, Jimin and
Lee, Yongjae and
Ananiadou, Sophia and
Chen, Hsin-Hsi and
Takamura, Hiroya and
Chen, Chung-Chi",
booktitle = "Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.finnlp-1.66/",
pages = "755--761",
ISBN = "979-8-89176-466-8",
abstract = "Financial question answering demands rigorous synthesis of standardized SEC filings alongside unstructured, cross-document text. This complexity is significantly amplified in multilingual environments, where terminology and reporting conventions vary across languages. We present a two-stage pipeline for the FinNLP 2026 PolyFiQA shared task, with all inference routed through the OpenRouter API under the 70B parameter limit. Stage 1 uses Qwen3.8-27B with category-calibrated few-shot prompts to extract facts and synthesize news across five languages (English, Chinese, Japanese, Spanish, Greek). Stage 2 is an LLM-as-a-Judge formatting guard that checks format compliance, strips filler, and verifies citations, without rewriting content. On our 76-instance training/development set (used for both calibration and evaluation, no held-out split), the calibrated pipeline reaches 48.19{\%} Macro ROUGE-1 F1, an 88.3{\%} relative gain over a zero-shot 70B baseline and a 6.32-point margin over Llama-3-70B{'}s own few-shot result. Gains concentrate in categories needing narrative synthesis (Revenue Trends, Cash Flow Dynamics) and are smaller for terse, formulaic ones (R D Investments). On the official blind test set, our system scores 37.02{\%} macro ROUGE-1 F1 on the private leaderboard (52 instances) and 31.79{\%} on the public slice (24 instances)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="atiq-butt-2026-ahsanblah">
<titleInfo>
<title>AhsanBLAH at the FinEval 2026: Grounded Two-Stage Financial QA with LLM-Judge Verification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Ahsan</namePart>
<namePart type="family">Atiq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohib</namePart>
<namePart type="given">Ahmad</namePart>
<namePart type="family">Butt</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>Financial question answering demands rigorous synthesis of standardized SEC filings alongside unstructured, cross-document text. This complexity is significantly amplified in multilingual environments, where terminology and reporting conventions vary across languages. We present a two-stage pipeline for the FinNLP 2026 PolyFiQA shared task, with all inference routed through the OpenRouter API under the 70B parameter limit. Stage 1 uses Qwen3.8-27B with category-calibrated few-shot prompts to extract facts and synthesize news across five languages (English, Chinese, Japanese, Spanish, Greek). Stage 2 is an LLM-as-a-Judge formatting guard that checks format compliance, strips filler, and verifies citations, without rewriting content. On our 76-instance training/development set (used for both calibration and evaluation, no held-out split), the calibrated pipeline reaches 48.19% Macro ROUGE-1 F1, an 88.3% relative gain over a zero-shot 70B baseline and a 6.32-point margin over Llama-3-70B’s own few-shot result. Gains concentrate in categories needing narrative synthesis (Revenue Trends, Cash Flow Dynamics) and are smaller for terse, formulaic ones (R D Investments). On the official blind test set, our system scores 37.02% macro ROUGE-1 F1 on the private leaderboard (52 instances) and 31.79% on the public slice (24 instances).</abstract>
<identifier type="citekey">atiq-butt-2026-ahsanblah</identifier>
<location>
<url>https://aclanthology.org/2026.finnlp-1.66/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>755</start>
<end>761</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AhsanBLAH at the FinEval 2026: Grounded Two-Stage Financial QA with LLM-Judge Verification
%A Atiq, Muhammad Ahsan
%A Butt, Mohib Ahmad
%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 atiq-butt-2026-ahsanblah
%X Financial question answering demands rigorous synthesis of standardized SEC filings alongside unstructured, cross-document text. This complexity is significantly amplified in multilingual environments, where terminology and reporting conventions vary across languages. We present a two-stage pipeline for the FinNLP 2026 PolyFiQA shared task, with all inference routed through the OpenRouter API under the 70B parameter limit. Stage 1 uses Qwen3.8-27B with category-calibrated few-shot prompts to extract facts and synthesize news across five languages (English, Chinese, Japanese, Spanish, Greek). Stage 2 is an LLM-as-a-Judge formatting guard that checks format compliance, strips filler, and verifies citations, without rewriting content. On our 76-instance training/development set (used for both calibration and evaluation, no held-out split), the calibrated pipeline reaches 48.19% Macro ROUGE-1 F1, an 88.3% relative gain over a zero-shot 70B baseline and a 6.32-point margin over Llama-3-70B’s own few-shot result. Gains concentrate in categories needing narrative synthesis (Revenue Trends, Cash Flow Dynamics) and are smaller for terse, formulaic ones (R D Investments). On the official blind test set, our system scores 37.02% macro ROUGE-1 F1 on the private leaderboard (52 instances) and 31.79% on the public slice (24 instances).
%U https://aclanthology.org/2026.finnlp-1.66/
%P 755-761
Markdown (Informal)
[AhsanBLAH at the FinEval 2026: Grounded Two-Stage Financial QA with LLM-Judge Verification](https://aclanthology.org/2026.finnlp-1.66/) (Atiq & Butt, FinNLP 2026)
ACL