@inproceedings{zhang-2026-llm,
title = "{LLM}-Based Frame and Stance Annotation for 19th-Century Rumour Discourse in {US} and {UK} Newspapers",
author = "Zhang, Wanshu",
editor = "Oleskeviciene, Giedre Valunaite and
Giouli, Voula and
Armaselu, Florentina and
Liebeskind, Chaya and
McGillivray, Barbara",
booktitle = "Proceedings of the Workshop Neology and Large Language Models",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.neollm-1.8/",
doi = "10.63317/4qdnrzfmibbz",
pages = "66--70",
abstract = "Large language models (LLMs) are increasingly used for lexicographic support, neology detection, and semantic categorization, yet their behaviour on historical newspapers remains under-evaluated. This short paper describes an ongoing project that extends a DH2026-accepted two-phase methodology for extracting and tracking rumours in historical newspapers. From large-scale US and UK corpora (PleIAs/US-PD-Newspapers; biglam/hmd{\_}newspapers), the DH workflow produces gold-standard sentence-level rumour instances with proposition-like ``rumour content'' spans (Rumour{\_}Content/Cleaned{\_}Content) and extraction-pattern metadata. Building on these historically grounded units, we propose an LLM-centered benchmark and analysis pipeline for assigning topical frames and evidential stance to rumour propositions, and for auditing ``temporal projection'' when models introduce anachronistic modern misinformation framings. For controlled cross-variety comparison we construct a strictly balanced benchmark of 800 instances over two well-attested bins (1840{--}1859, 1860{--}1879) and both national varieties (200 per country per bin). We outline prompt conditions (text-only vs time-aware vs historically calibrated) and self-consistency voting to quantify label stability and error modes. A small manually annotated subset supports evaluation, while the main contribution is the benchmark design, prompts, and reproducible protocol enabling community feedback before full-scale results are finalized."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-2026-llm">
<titleInfo>
<title>LLM-Based Frame and Stance Annotation for 19th-Century Rumour Discourse in US and UK Newspapers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanshu</namePart>
<namePart type="family">Zhang</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>Proceedings of the Workshop Neology and Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giedre</namePart>
<namePart type="given">Valunaite</namePart>
<namePart type="family">Oleskeviciene</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Voula</namePart>
<namePart type="family">Giouli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Florentina</namePart>
<namePart type="family">Armaselu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaya</namePart>
<namePart type="family">Liebeskind</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">McGillivray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) are increasingly used for lexicographic support, neology detection, and semantic categorization, yet their behaviour on historical newspapers remains under-evaluated. This short paper describes an ongoing project that extends a DH2026-accepted two-phase methodology for extracting and tracking rumours in historical newspapers. From large-scale US and UK corpora (PleIAs/US-PD-Newspapers; biglam/hmd_newspapers), the DH workflow produces gold-standard sentence-level rumour instances with proposition-like “rumour content” spans (Rumour_Content/Cleaned_Content) and extraction-pattern metadata. Building on these historically grounded units, we propose an LLM-centered benchmark and analysis pipeline for assigning topical frames and evidential stance to rumour propositions, and for auditing “temporal projection” when models introduce anachronistic modern misinformation framings. For controlled cross-variety comparison we construct a strictly balanced benchmark of 800 instances over two well-attested bins (1840–1859, 1860–1879) and both national varieties (200 per country per bin). We outline prompt conditions (text-only vs time-aware vs historically calibrated) and self-consistency voting to quantify label stability and error modes. A small manually annotated subset supports evaluation, while the main contribution is the benchmark design, prompts, and reproducible protocol enabling community feedback before full-scale results are finalized.</abstract>
<identifier type="citekey">zhang-2026-llm</identifier>
<identifier type="doi">10.63317/4qdnrzfmibbz</identifier>
<location>
<url>https://aclanthology.org/2026.neollm-1.8/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>66</start>
<end>70</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLM-Based Frame and Stance Annotation for 19th-Century Rumour Discourse in US and UK Newspapers
%A Zhang, Wanshu
%Y Oleskeviciene, Giedre Valunaite
%Y Giouli, Voula
%Y Armaselu, Florentina
%Y Liebeskind, Chaya
%Y McGillivray, Barbara
%S Proceedings of the Workshop Neology and Large Language Models
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F zhang-2026-llm
%X Large language models (LLMs) are increasingly used for lexicographic support, neology detection, and semantic categorization, yet their behaviour on historical newspapers remains under-evaluated. This short paper describes an ongoing project that extends a DH2026-accepted two-phase methodology for extracting and tracking rumours in historical newspapers. From large-scale US and UK corpora (PleIAs/US-PD-Newspapers; biglam/hmd_newspapers), the DH workflow produces gold-standard sentence-level rumour instances with proposition-like “rumour content” spans (Rumour_Content/Cleaned_Content) and extraction-pattern metadata. Building on these historically grounded units, we propose an LLM-centered benchmark and analysis pipeline for assigning topical frames and evidential stance to rumour propositions, and for auditing “temporal projection” when models introduce anachronistic modern misinformation framings. For controlled cross-variety comparison we construct a strictly balanced benchmark of 800 instances over two well-attested bins (1840–1859, 1860–1879) and both national varieties (200 per country per bin). We outline prompt conditions (text-only vs time-aware vs historically calibrated) and self-consistency voting to quantify label stability and error modes. A small manually annotated subset supports evaluation, while the main contribution is the benchmark design, prompts, and reproducible protocol enabling community feedback before full-scale results are finalized.
%R 10.63317/4qdnrzfmibbz
%U https://aclanthology.org/2026.neollm-1.8/
%U https://doi.org/10.63317/4qdnrzfmibbz
%P 66-70
Markdown (Informal)
[LLM-Based Frame and Stance Annotation for 19th-Century Rumour Discourse in US and UK Newspapers](https://aclanthology.org/2026.neollm-1.8/) (Zhang, NeoLLM 2026)
ACL