@inproceedings{yuksel-etal-2026-uncertainty,
title = "Uncertainty Quantification to Improve the Reliability of {LLM}-Based Hate Speech Detection",
author = "Yuksel, Nehir Idil and
Dementieva, Daryna and
Fraser, Alexander",
editor = "Atwell, Katherine and
Borah, Angana and
Dementieva, Daryna and
Kreiss, Elisa and
Kotonya, Neema and
Liu, Jiarui and
Olson, Liz and
Wan, Ruyuan and
Zhao, Jieyu",
booktitle = "Proceedings of the Fifth Workshop on {NLP} for Positive Impact ({NLP}4{PI})",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nlp4pi-1.41/",
pages = "544--574",
ISBN = "979-8-89176-495-8",
abstract = "While Large Language Models (LLMs) have been tested for hate speech detection, their reliability in subjective annotation settings remains underexplored. Existing improved prompting approaches for hate speech classification often rely on continuous context retrieval, which can be computationally expensive and unnecessary for confident predictions. To address this, we propose an uncertainty-aware prompting pipeline that integrates Uncertainty Quantification (UQ) into LLM-based hate speech classification. The framework uses uncertainty scores to identify ambiguous and potentially unreliable predictions through threshold-based filtering, enabling selective application of advanced context-enriched prompting only when needed. We evaluate the approach on two benchmark datasets{---}Measuring Hate Speech (Sachdeva et al., 2022) and CREHate (Lee et al., 2024{---}across five LLMs using two advanced prompting strategies: Persona-Aware and Annotation-Grounded Few-Shot Prompting. Experimental results show that the proposed pipeline consistently improves classification performance and reduces uncertainty, leading to more reliable model behavior with improved computational efficiency."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yuksel-etal-2026-uncertainty">
<titleInfo>
<title>Uncertainty Quantification to Improve the Reliability of LLM-Based Hate Speech Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nehir</namePart>
<namePart type="given">Idil</namePart>
<namePart type="family">Yuksel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daryna</namePart>
<namePart type="family">Dementieva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Fraser</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 Fifth Workshop on NLP for Positive Impact (NLP4PI)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katherine</namePart>
<namePart type="family">Atwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angana</namePart>
<namePart type="family">Borah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daryna</namePart>
<namePart type="family">Dementieva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Kreiss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neema</namePart>
<namePart type="family">Kotonya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiarui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liz</namePart>
<namePart type="family">Olson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruyuan</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieyu</namePart>
<namePart type="family">Zhao</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">979-8-89176-495-8</identifier>
</relatedItem>
<abstract>While Large Language Models (LLMs) have been tested for hate speech detection, their reliability in subjective annotation settings remains underexplored. Existing improved prompting approaches for hate speech classification often rely on continuous context retrieval, which can be computationally expensive and unnecessary for confident predictions. To address this, we propose an uncertainty-aware prompting pipeline that integrates Uncertainty Quantification (UQ) into LLM-based hate speech classification. The framework uses uncertainty scores to identify ambiguous and potentially unreliable predictions through threshold-based filtering, enabling selective application of advanced context-enriched prompting only when needed. We evaluate the approach on two benchmark datasets—Measuring Hate Speech (Sachdeva et al., 2022) and CREHate (Lee et al., 2024—across five LLMs using two advanced prompting strategies: Persona-Aware and Annotation-Grounded Few-Shot Prompting. Experimental results show that the proposed pipeline consistently improves classification performance and reduces uncertainty, leading to more reliable model behavior with improved computational efficiency.</abstract>
<identifier type="citekey">yuksel-etal-2026-uncertainty</identifier>
<location>
<url>https://aclanthology.org/2026.nlp4pi-1.41/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>544</start>
<end>574</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Uncertainty Quantification to Improve the Reliability of LLM-Based Hate Speech Detection
%A Yuksel, Nehir Idil
%A Dementieva, Daryna
%A Fraser, Alexander
%Y Atwell, Katherine
%Y Borah, Angana
%Y Dementieva, Daryna
%Y Kreiss, Elisa
%Y Kotonya, Neema
%Y Liu, Jiarui
%Y Olson, Liz
%Y Wan, Ruyuan
%Y Zhao, Jieyu
%S Proceedings of the Fifth Workshop on NLP for Positive Impact (NLP4PI)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-495-8
%F yuksel-etal-2026-uncertainty
%X While Large Language Models (LLMs) have been tested for hate speech detection, their reliability in subjective annotation settings remains underexplored. Existing improved prompting approaches for hate speech classification often rely on continuous context retrieval, which can be computationally expensive and unnecessary for confident predictions. To address this, we propose an uncertainty-aware prompting pipeline that integrates Uncertainty Quantification (UQ) into LLM-based hate speech classification. The framework uses uncertainty scores to identify ambiguous and potentially unreliable predictions through threshold-based filtering, enabling selective application of advanced context-enriched prompting only when needed. We evaluate the approach on two benchmark datasets—Measuring Hate Speech (Sachdeva et al., 2022) and CREHate (Lee et al., 2024—across five LLMs using two advanced prompting strategies: Persona-Aware and Annotation-Grounded Few-Shot Prompting. Experimental results show that the proposed pipeline consistently improves classification performance and reduces uncertainty, leading to more reliable model behavior with improved computational efficiency.
%U https://aclanthology.org/2026.nlp4pi-1.41/
%P 544-574
Markdown (Informal)
[Uncertainty Quantification to Improve the Reliability of LLM-Based Hate Speech Detection](https://aclanthology.org/2026.nlp4pi-1.41/) (Yuksel et al., NLP4PI 2026)
ACL