@inproceedings{chuang-etal-2026-detecting,
title = "Detecting Potentially Under-annotated Explicit Discourse Connectives in the {P}enn {D}iscourse {T}reebank ({PDTB}-3) with {LLM}s",
author = "Chuang, Yueh-Ting and
Liao, Xixian and
Webber, Bonnie",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.158/",
doi = "10.63317/5392qqgkyzs5",
pages = "2012--2023",
abstract = "Accurate identification of explicit discourse connectives is crucial for analysing discourse relations, which supports NLP tasks such as summarisation and question answering. However, annotation inconsistencies remain a challenge, particularly for ambiguous prepositions with both discourse and non-discourse usages. This paper presents a pipeline that leverages large language model (LLM) prompting, cross-model agreement, and syntactic pattern analysis to detect likely under-annotated connectives. Evaluated on four prepositions (by, with, without and for), the approach effectively identifies likely under-annotations for some, but not all prepositions. Results show that while the method is promising, its generalisability depends on improved prompt design, model choice, and syntactic analysis tools. The findings highlight both the potential and limitations of LLM-based approaches for corpus error detection and demonstrate how improved discourse annotation can contribute to more reliable data for downstream NLP tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chuang-etal-2026-detecting">
<titleInfo>
<title>Detecting Potentially Under-annotated Explicit Discourse Connectives in the Penn Discourse Treebank (PDTB-3) with LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yueh-Ting</namePart>
<namePart type="family">Chuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xixian</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</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 Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Accurate identification of explicit discourse connectives is crucial for analysing discourse relations, which supports NLP tasks such as summarisation and question answering. However, annotation inconsistencies remain a challenge, particularly for ambiguous prepositions with both discourse and non-discourse usages. This paper presents a pipeline that leverages large language model (LLM) prompting, cross-model agreement, and syntactic pattern analysis to detect likely under-annotated connectives. Evaluated on four prepositions (by, with, without and for), the approach effectively identifies likely under-annotations for some, but not all prepositions. Results show that while the method is promising, its generalisability depends on improved prompt design, model choice, and syntactic analysis tools. The findings highlight both the potential and limitations of LLM-based approaches for corpus error detection and demonstrate how improved discourse annotation can contribute to more reliable data for downstream NLP tasks.</abstract>
<identifier type="citekey">chuang-etal-2026-detecting</identifier>
<identifier type="doi">10.63317/5392qqgkyzs5</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.158/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>2012</start>
<end>2023</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detecting Potentially Under-annotated Explicit Discourse Connectives in the Penn Discourse Treebank (PDTB-3) with LLMs
%A Chuang, Yueh-Ting
%A Liao, Xixian
%A Webber, Bonnie
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F chuang-etal-2026-detecting
%X Accurate identification of explicit discourse connectives is crucial for analysing discourse relations, which supports NLP tasks such as summarisation and question answering. However, annotation inconsistencies remain a challenge, particularly for ambiguous prepositions with both discourse and non-discourse usages. This paper presents a pipeline that leverages large language model (LLM) prompting, cross-model agreement, and syntactic pattern analysis to detect likely under-annotated connectives. Evaluated on four prepositions (by, with, without and for), the approach effectively identifies likely under-annotations for some, but not all prepositions. Results show that while the method is promising, its generalisability depends on improved prompt design, model choice, and syntactic analysis tools. The findings highlight both the potential and limitations of LLM-based approaches for corpus error detection and demonstrate how improved discourse annotation can contribute to more reliable data for downstream NLP tasks.
%R 10.63317/5392qqgkyzs5
%U https://aclanthology.org/2026.lrec-1.158/
%U https://doi.org/10.63317/5392qqgkyzs5
%P 2012-2023
Markdown (Informal)
[Detecting Potentially Under-annotated Explicit Discourse Connectives in the Penn Discourse Treebank (PDTB-3) with LLMs](https://aclanthology.org/2026.lrec-1.158/) (Chuang et al., LREC 2026)
ACL