@inproceedings{petrocelli-etal-2026-experts,
title = "From Experts to Open-Weight Models: a Validated {LLM} Pipeline for Institutional Economic News Annotation",
author = "Petrocelli, Michele and
Rollin, Andrea and
Berta, Matteo and
Zafonte, Francesca and
Monaco, Simone and
Apiletti, Daniele and
Cerquitelli, Tania",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.231/",
pages = "3854--3869",
ISBN = "979-8-89176-460-6",
abstract = "Economic sentiment plays a central role in shaping perceptions of economic conditions, influencing economic behavior, and policy decisions. Recent advances in large language models have made large-scale sentiment extraction from news increasingly feasible, driving its growing use in economic analysis and forecasting systems across national public-sector institutions. Existing approaches scale mainly through automated or weakly supervised labeling, sacrificing expert alignment and domain nuance, and treat sentiment in isolation, overlooking complementary annotations, such as topic, needed to capture structured economic signals for downstream forecasting. To address these limitations, we introduce a human-annotated dataset of Italian economic news labeled by domain experts for sentiment and topic, and develop a statistically validated pipeline that uses few-shot prompting of commercial large language models to expand coverage while preserving expert alignment at scale. We fine-tune multiple open-weight models on the resulting corpus, yielding language specific annotation models that maintain high expert agreement across architectures and satisfy the reproducibility and governance requirements of national public-sector institutions. Starting from 800 expert-labeled articles, the pipeline produces approximately 9,200 additional expert-aligned labels and trains local models that pass the Alternative Annotator Test for both sentiment and topic classification. A subset of the annotated dataset is publicly released to support further research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="petrocelli-etal-2026-experts">
<titleInfo>
<title>From Experts to Open-Weight Models: a Validated LLM Pipeline for Institutional Economic News Annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="family">Petrocelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Rollin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Berta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesca</namePart>
<namePart type="family">Zafonte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Monaco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniele</namePart>
<namePart type="family">Apiletti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tania</namePart>
<namePart type="family">Cerquitelli</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: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</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">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>Economic sentiment plays a central role in shaping perceptions of economic conditions, influencing economic behavior, and policy decisions. Recent advances in large language models have made large-scale sentiment extraction from news increasingly feasible, driving its growing use in economic analysis and forecasting systems across national public-sector institutions. Existing approaches scale mainly through automated or weakly supervised labeling, sacrificing expert alignment and domain nuance, and treat sentiment in isolation, overlooking complementary annotations, such as topic, needed to capture structured economic signals for downstream forecasting. To address these limitations, we introduce a human-annotated dataset of Italian economic news labeled by domain experts for sentiment and topic, and develop a statistically validated pipeline that uses few-shot prompting of commercial large language models to expand coverage while preserving expert alignment at scale. We fine-tune multiple open-weight models on the resulting corpus, yielding language specific annotation models that maintain high expert agreement across architectures and satisfy the reproducibility and governance requirements of national public-sector institutions. Starting from 800 expert-labeled articles, the pipeline produces approximately 9,200 additional expert-aligned labels and trains local models that pass the Alternative Annotator Test for both sentiment and topic classification. A subset of the annotated dataset is publicly released to support further research.</abstract>
<identifier type="citekey">petrocelli-etal-2026-experts</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.231/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>3854</start>
<end>3869</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Experts to Open-Weight Models: a Validated LLM Pipeline for Institutional Economic News Annotation
%A Petrocelli, Michele
%A Rollin, Andrea
%A Berta, Matteo
%A Zafonte, Francesca
%A Monaco, Simone
%A Apiletti, Daniele
%A Cerquitelli, Tania
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F petrocelli-etal-2026-experts
%X Economic sentiment plays a central role in shaping perceptions of economic conditions, influencing economic behavior, and policy decisions. Recent advances in large language models have made large-scale sentiment extraction from news increasingly feasible, driving its growing use in economic analysis and forecasting systems across national public-sector institutions. Existing approaches scale mainly through automated or weakly supervised labeling, sacrificing expert alignment and domain nuance, and treat sentiment in isolation, overlooking complementary annotations, such as topic, needed to capture structured economic signals for downstream forecasting. To address these limitations, we introduce a human-annotated dataset of Italian economic news labeled by domain experts for sentiment and topic, and develop a statistically validated pipeline that uses few-shot prompting of commercial large language models to expand coverage while preserving expert alignment at scale. We fine-tune multiple open-weight models on the resulting corpus, yielding language specific annotation models that maintain high expert agreement across architectures and satisfy the reproducibility and governance requirements of national public-sector institutions. Starting from 800 expert-labeled articles, the pipeline produces approximately 9,200 additional expert-aligned labels and trains local models that pass the Alternative Annotator Test for both sentiment and topic classification. A subset of the annotated dataset is publicly released to support further research.
%U https://aclanthology.org/2026.emnlp-industry.231/
%P 3854-3869
Markdown (Informal)
[From Experts to Open-Weight Models: a Validated LLM Pipeline for Institutional Economic News Annotation](https://aclanthology.org/2026.emnlp-industry.231/) (Petrocelli et al., EMNLP 2026)
ACL