@inproceedings{attak-etal-2026-improving,
title = "Improving Verbatim Financial Causality Extraction with Supervised Fine-Tuning and Prompt Repetition",
author = "Attak, Sanae and
Chiadmi, Mohammed Salah and
Lamrani Alaoui, Youssef",
editor = "El-Haj, Mo and
Moreno Sandoval, Antonio and
Garcia-Serrano, Ana and
Chen, Chung-Chi and
Rayson, Paul and
Torterolo Orta, Yanco Amor and
Martinez, Paloma and
Porta, Jordi",
booktitle = "The 7th Financial Narrative Processing Workshop",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.fnp-1.16/",
doi = "10.63317/2d873tuemyhc",
pages = "152--159",
abstract = "This paper investigates the application of generative Large Language Models (LLMs) for strict verbatim span extraction. We evaluate our methodology within the FinCausal 2026 shared task. Because generative LLMs optimize next-token probability rather than strict boundaries, they naturally suffer from over-generation and boundary drift in extraction tasks. To address this, we introduce a generalized structural training constraint, extending prompt repetition from a purely inference-time heuristic to a training-time supervision framework. By incorporating duplicated prompts directly into Supervised Fine-Tuning (SFT), we hypothesize that this encourages the model to internalize a form of unidirectional cross-reading behavior, leading to stronger alignment between generated spans and the source context for exact extraction. Evaluating on open-weights (Qwen2.5-14B-Instruct-1M) and proprietary (GPT-4.1-Nano) architectures, we find this soft attention constraint improves Exact Match scores for open models and helps balance cross-lingual performance disparities. Conversely, the proprietary model exhibited sensitivity to prompt duplication, achieving its highest score without repetition. Ultimately, our deterministic SFT approach secured 4th place in the Spanish subtask (4.73) and 6th place in the English subtask (4.70), indicating the viability of structurally simple, natively fine-tuned models compared to complex multi-stage pipelines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="attak-etal-2026-improving">
<titleInfo>
<title>Improving Verbatim Financial Causality Extraction with Supervised Fine-Tuning and Prompt Repetition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanae</namePart>
<namePart type="family">Attak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Salah</namePart>
<namePart type="family">Chiadmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youssef</namePart>
<namePart type="family">Lamrani Alaoui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The 7th Financial Narrative Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mo</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Moreno Sandoval</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="family">Garcia-Serrano</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>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanco</namePart>
<namePart type="given">Amor</namePart>
<namePart type="family">Torterolo Orta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paloma</namePart>
<namePart type="family">Martinez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordi</namePart>
<namePart type="family">Porta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper investigates the application of generative Large Language Models (LLMs) for strict verbatim span extraction. We evaluate our methodology within the FinCausal 2026 shared task. Because generative LLMs optimize next-token probability rather than strict boundaries, they naturally suffer from over-generation and boundary drift in extraction tasks. To address this, we introduce a generalized structural training constraint, extending prompt repetition from a purely inference-time heuristic to a training-time supervision framework. By incorporating duplicated prompts directly into Supervised Fine-Tuning (SFT), we hypothesize that this encourages the model to internalize a form of unidirectional cross-reading behavior, leading to stronger alignment between generated spans and the source context for exact extraction. Evaluating on open-weights (Qwen2.5-14B-Instruct-1M) and proprietary (GPT-4.1-Nano) architectures, we find this soft attention constraint improves Exact Match scores for open models and helps balance cross-lingual performance disparities. Conversely, the proprietary model exhibited sensitivity to prompt duplication, achieving its highest score without repetition. Ultimately, our deterministic SFT approach secured 4th place in the Spanish subtask (4.73) and 6th place in the English subtask (4.70), indicating the viability of structurally simple, natively fine-tuned models compared to complex multi-stage pipelines.</abstract>
<identifier type="citekey">attak-etal-2026-improving</identifier>
<identifier type="doi">10.63317/2d873tuemyhc</identifier>
<location>
<url>https://aclanthology.org/2026.fnp-1.16/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>152</start>
<end>159</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Verbatim Financial Causality Extraction with Supervised Fine-Tuning and Prompt Repetition
%A Attak, Sanae
%A Chiadmi, Mohammed Salah
%A Lamrani Alaoui, Youssef
%Y El-Haj, Mo
%Y Moreno Sandoval, Antonio
%Y Garcia-Serrano, Ana
%Y Chen, Chung-Chi
%Y Rayson, Paul
%Y Torterolo Orta, Yanco Amor
%Y Martinez, Paloma
%Y Porta, Jordi
%S The 7th Financial Narrative Processing Workshop
%D 2026
%8 May
%I European Language Resources Association (ELRA)
%C Palma de Mallorca, Spain
%F attak-etal-2026-improving
%X This paper investigates the application of generative Large Language Models (LLMs) for strict verbatim span extraction. We evaluate our methodology within the FinCausal 2026 shared task. Because generative LLMs optimize next-token probability rather than strict boundaries, they naturally suffer from over-generation and boundary drift in extraction tasks. To address this, we introduce a generalized structural training constraint, extending prompt repetition from a purely inference-time heuristic to a training-time supervision framework. By incorporating duplicated prompts directly into Supervised Fine-Tuning (SFT), we hypothesize that this encourages the model to internalize a form of unidirectional cross-reading behavior, leading to stronger alignment between generated spans and the source context for exact extraction. Evaluating on open-weights (Qwen2.5-14B-Instruct-1M) and proprietary (GPT-4.1-Nano) architectures, we find this soft attention constraint improves Exact Match scores for open models and helps balance cross-lingual performance disparities. Conversely, the proprietary model exhibited sensitivity to prompt duplication, achieving its highest score without repetition. Ultimately, our deterministic SFT approach secured 4th place in the Spanish subtask (4.73) and 6th place in the English subtask (4.70), indicating the viability of structurally simple, natively fine-tuned models compared to complex multi-stage pipelines.
%R 10.63317/2d873tuemyhc
%U https://aclanthology.org/2026.fnp-1.16/
%U https://doi.org/10.63317/2d873tuemyhc
%P 152-159
Markdown (Informal)
[Improving Verbatim Financial Causality Extraction with Supervised Fine-Tuning and Prompt Repetition](https://aclanthology.org/2026.fnp-1.16/) (Attak et al., FNP 2026)
ACL