@inproceedings{krasselt-etal-2026-still,
title = "Do We Still Need Corpora and Corpus Analysis Platforms? Discourse Analysis in Times of {LLM}s",
author = "Krasselt, Julia and
Lemmenmeier-Batini{\'c}, Dolores and
Dreesen, Philipp",
editor = "Montejo-Raez, Arturo and
Grisot, Cristina and
Blochowiak, Joanna and
Ljube{\v{s}}i{\'c}, Nikola and
Battaner, Elena and
Rigau, German",
booktitle = "Proceedings of Shaping Multilingual, Multimodal {AI} for the Social Sciences and Humanities ({LLM}s4{SSH}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma de Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.llms4ssh-1.7/",
doi = "10.63317/3qjxyff7rp9n",
pages = "67--72",
abstract = "Corpus-based discourse analysis investigates the linguistic construction of societally shared knowledge by iterating between quantitative pattern detection and qualitative interpretation in large text collections. Large Language Models (LLMs) promise to lower practical barriers to such work (e.g., natural-language querying, qualitative coding), yet they also introduce risks that are especially consequential in discourse-analytic settings, where fluent summaries can encourage ungrounded interpretation. This position paper argues that integrating LLMs into corpus analysis platforms is appropriate only insofar as it remains compatible with three epistemic premises of corpus research: (1) transparency of the data basis and traceability of analytical operations; (2) interpretability as evidence-constrained sense-making; and (3) seriality and patternedness as distributional structure and variation. In this opinion paper, we contribute a platform-oriented requirements perspective that translates these premises into design constraints for tool-calling/RAG-style integration, and we outline implementation directions that treat LLMs as an interaction layer over inspectable corpus retrieval and platform-based analysis."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krasselt-etal-2026-still">
<titleInfo>
<title>Do We Still Need Corpora and Corpus Analysis Platforms? Discourse Analysis in Times of LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Krasselt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dolores</namePart>
<namePart type="family">Lemmenmeier-Batinić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Dreesen</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 Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Montejo-Raez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Grisot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joanna</namePart>
<namePart type="family">Blochowiak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Battaner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Rigau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Corpus-based discourse analysis investigates the linguistic construction of societally shared knowledge by iterating between quantitative pattern detection and qualitative interpretation in large text collections. Large Language Models (LLMs) promise to lower practical barriers to such work (e.g., natural-language querying, qualitative coding), yet they also introduce risks that are especially consequential in discourse-analytic settings, where fluent summaries can encourage ungrounded interpretation. This position paper argues that integrating LLMs into corpus analysis platforms is appropriate only insofar as it remains compatible with three epistemic premises of corpus research: (1) transparency of the data basis and traceability of analytical operations; (2) interpretability as evidence-constrained sense-making; and (3) seriality and patternedness as distributional structure and variation. In this opinion paper, we contribute a platform-oriented requirements perspective that translates these premises into design constraints for tool-calling/RAG-style integration, and we outline implementation directions that treat LLMs as an interaction layer over inspectable corpus retrieval and platform-based analysis.</abstract>
<identifier type="citekey">krasselt-etal-2026-still</identifier>
<identifier type="doi">10.63317/3qjxyff7rp9n</identifier>
<location>
<url>https://aclanthology.org/2026.llms4ssh-1.7/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>67</start>
<end>72</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do We Still Need Corpora and Corpus Analysis Platforms? Discourse Analysis in Times of LLMs
%A Krasselt, Julia
%A Lemmenmeier-Batinić, Dolores
%A Dreesen, Philipp
%Y Montejo-Raez, Arturo
%Y Grisot, Cristina
%Y Blochowiak, Joanna
%Y Ljubešić, Nikola
%Y Battaner, Elena
%Y Rigau, German
%S Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca (Spain)
%F krasselt-etal-2026-still
%X Corpus-based discourse analysis investigates the linguistic construction of societally shared knowledge by iterating between quantitative pattern detection and qualitative interpretation in large text collections. Large Language Models (LLMs) promise to lower practical barriers to such work (e.g., natural-language querying, qualitative coding), yet they also introduce risks that are especially consequential in discourse-analytic settings, where fluent summaries can encourage ungrounded interpretation. This position paper argues that integrating LLMs into corpus analysis platforms is appropriate only insofar as it remains compatible with three epistemic premises of corpus research: (1) transparency of the data basis and traceability of analytical operations; (2) interpretability as evidence-constrained sense-making; and (3) seriality and patternedness as distributional structure and variation. In this opinion paper, we contribute a platform-oriented requirements perspective that translates these premises into design constraints for tool-calling/RAG-style integration, and we outline implementation directions that treat LLMs as an interaction layer over inspectable corpus retrieval and platform-based analysis.
%R 10.63317/3qjxyff7rp9n
%U https://aclanthology.org/2026.llms4ssh-1.7/
%U https://doi.org/10.63317/3qjxyff7rp9n
%P 67-72
Markdown (Informal)
[Do We Still Need Corpora and Corpus Analysis Platforms? Discourse Analysis in Times of LLMs](https://aclanthology.org/2026.llms4ssh-1.7/) (Krasselt et al., LLMs4SSH 2026)
ACL