@inproceedings{schlee-etal-2026-labelfusion,
title = "{L}abel{F}usion: Fusing Large Language Models with Transformer Encoders for Robust Financial News Classification",
author = {Schlee, Michael and
Weisser, Christoph and
Kivim{\"a}ki, Timo and
Mashiku, Melchizedek and
Saefken, Benjamin},
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-1.9/",
doi = "10.63317/5k4dk6iczjq5",
pages = "98--105",
abstract = "Financial news plays a central role in shaping investor sentiment and short-term dynamics in commodity markets. Many downstream financial applications{---}such as commodity price prediction or sentiment modeling{---}therefore rely on the ability to automatically identify news articles that are relevant to specific assets. However, obtaining large labeled corpora for financial text classification tasks is costly, and transformer-based classifiers such as RoBERTa often degrade significantly in low-data regimes. Our results show that appropriately prompted out-of-the-box large language models (LLMs) achieve strong performance even in low-data regimes. Furthermore, we propose LabelFusion, a hybrid architecture that combines the output of a prompt-engineered LLM with contextual embeddings produced by a fine-tuned RoBERTa encoder through a lightweight multilayer perceptron (MLP) voting layer. Evaluated on a ten-class multi-label subset of the Reuters-21578 corpus, LabelFusion achieves a macro F1 score of 96.0{\%} and an accuracy of 92.3{\%} when trained on the full dataset, outperforming both standalone RoBERTa (F1 94.6{\%}) and the standalone LLM (F1 93.9{\%}). In low- to mid-data regimes, however, the LLM alone proves surprisingly competitive, achieving an F1 score of 75.9{\%} even in a zero-shot setting and consistently outperforming LabelFusion until approximately 80{\%} of the training data is available. These results suggest that LLM-only prompting represents the preferred strategy under annotation constraints, whereas LabelFusion becomes the most effective solution once sufficient labeled data is available to train the encoder component. The code is available in an anonymized repository."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schlee-etal-2026-labelfusion">
<titleInfo>
<title>LabelFusion: Fusing Large Language Models with Transformer Encoders for Robust Financial News Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Schlee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoph</namePart>
<namePart type="family">Weisser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timo</namePart>
<namePart type="family">Kivimäki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melchizedek</namePart>
<namePart type="family">Mashiku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Saefken</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>Financial news plays a central role in shaping investor sentiment and short-term dynamics in commodity markets. Many downstream financial applications—such as commodity price prediction or sentiment modeling—therefore rely on the ability to automatically identify news articles that are relevant to specific assets. However, obtaining large labeled corpora for financial text classification tasks is costly, and transformer-based classifiers such as RoBERTa often degrade significantly in low-data regimes. Our results show that appropriately prompted out-of-the-box large language models (LLMs) achieve strong performance even in low-data regimes. Furthermore, we propose LabelFusion, a hybrid architecture that combines the output of a prompt-engineered LLM with contextual embeddings produced by a fine-tuned RoBERTa encoder through a lightweight multilayer perceptron (MLP) voting layer. Evaluated on a ten-class multi-label subset of the Reuters-21578 corpus, LabelFusion achieves a macro F1 score of 96.0% and an accuracy of 92.3% when trained on the full dataset, outperforming both standalone RoBERTa (F1 94.6%) and the standalone LLM (F1 93.9%). In low- to mid-data regimes, however, the LLM alone proves surprisingly competitive, achieving an F1 score of 75.9% even in a zero-shot setting and consistently outperforming LabelFusion until approximately 80% of the training data is available. These results suggest that LLM-only prompting represents the preferred strategy under annotation constraints, whereas LabelFusion becomes the most effective solution once sufficient labeled data is available to train the encoder component. The code is available in an anonymized repository.</abstract>
<identifier type="citekey">schlee-etal-2026-labelfusion</identifier>
<identifier type="doi">10.63317/5k4dk6iczjq5</identifier>
<location>
<url>https://aclanthology.org/2026.fnp-1.9/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>98</start>
<end>105</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LabelFusion: Fusing Large Language Models with Transformer Encoders for Robust Financial News Classification
%A Schlee, Michael
%A Weisser, Christoph
%A Kivimäki, Timo
%A Mashiku, Melchizedek
%A Saefken, Benjamin
%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 schlee-etal-2026-labelfusion
%X Financial news plays a central role in shaping investor sentiment and short-term dynamics in commodity markets. Many downstream financial applications—such as commodity price prediction or sentiment modeling—therefore rely on the ability to automatically identify news articles that are relevant to specific assets. However, obtaining large labeled corpora for financial text classification tasks is costly, and transformer-based classifiers such as RoBERTa often degrade significantly in low-data regimes. Our results show that appropriately prompted out-of-the-box large language models (LLMs) achieve strong performance even in low-data regimes. Furthermore, we propose LabelFusion, a hybrid architecture that combines the output of a prompt-engineered LLM with contextual embeddings produced by a fine-tuned RoBERTa encoder through a lightweight multilayer perceptron (MLP) voting layer. Evaluated on a ten-class multi-label subset of the Reuters-21578 corpus, LabelFusion achieves a macro F1 score of 96.0% and an accuracy of 92.3% when trained on the full dataset, outperforming both standalone RoBERTa (F1 94.6%) and the standalone LLM (F1 93.9%). In low- to mid-data regimes, however, the LLM alone proves surprisingly competitive, achieving an F1 score of 75.9% even in a zero-shot setting and consistently outperforming LabelFusion until approximately 80% of the training data is available. These results suggest that LLM-only prompting represents the preferred strategy under annotation constraints, whereas LabelFusion becomes the most effective solution once sufficient labeled data is available to train the encoder component. The code is available in an anonymized repository.
%R 10.63317/5k4dk6iczjq5
%U https://aclanthology.org/2026.fnp-1.9/
%U https://doi.org/10.63317/5k4dk6iczjq5
%P 98-105
Markdown (Informal)
[LabelFusion: Fusing Large Language Models with Transformer Encoders for Robust Financial News Classification](https://aclanthology.org/2026.fnp-1.9/) (Schlee et al., FNP 2026)
ACL