@inproceedings{rivera-etal-2024-combining,
title = "Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation",
author = "Rivera, Mauricio and
Godbout, Jean-Fran{\c{c}}ois and
Rabbany, Reihaneh and
Pelrine, Kellin",
editor = {V{\'a}zquez, Ra{\'u}l and
Celikkanat, Hande and
Ulmer, Dennis and
Tiedemann, J{\"o}rg and
Swayamdipta, Swabha and
Aziz, Wilker and
Plank, Barbara and
Baan, Joris and
de Marneffe, Marie-Catherine},
booktitle = "Proceedings of the 1st Workshop on Uncertainty-Aware NLP (UncertaiNLP 2024)",
month = mar,
year = "2024",
address = "St Julians, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.uncertainlp-1.12",
pages = "114--126",
abstract = "Large Language Models have emerged as prime candidates to tackle misinformation mitigation. However, existing approaches struggle with hallucinations and overconfident predictions. We propose an uncertainty quantification framework that leverages both direct confidence elicitation and sampled-based consistency methods to provide better calibration for NLP misinformation mitigation solutions. We first investigate the calibration of sample-based consistency methods that exploit distinct features of consistency across sample sizes and stochastic levels. Next, we evaluate the performance and distributional shift of a robust numeric verbalization prompt across single vs. two-step confidence elicitation procedure. We also compare the performance of the same prompt with different versions of GPT and different numerical scales. Finally, we combine the sample-based consistency and verbalized methods to propose a hybrid framework that yields a better uncertainty estimation for GPT models. Overall, our work proposes novel uncertainty quantification methods that will improve the reliability of Large Language Models in misinformation mitigation applications.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rivera-etal-2024-combining">
<titleInfo>
<title>Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mauricio</namePart>
<namePart type="family">Rivera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean-François</namePart>
<namePart type="family">Godbout</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reihaneh</namePart>
<namePart type="family">Rabbany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kellin</namePart>
<namePart type="family">Pelrine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Uncertainty-Aware NLP (UncertaiNLP 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="family">Vázquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hande</namePart>
<namePart type="family">Celikkanat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dennis</namePart>
<namePart type="family">Ulmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wilker</namePart>
<namePart type="family">Aziz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joris</namePart>
<namePart type="family">Baan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St Julians, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models have emerged as prime candidates to tackle misinformation mitigation. However, existing approaches struggle with hallucinations and overconfident predictions. We propose an uncertainty quantification framework that leverages both direct confidence elicitation and sampled-based consistency methods to provide better calibration for NLP misinformation mitigation solutions. We first investigate the calibration of sample-based consistency methods that exploit distinct features of consistency across sample sizes and stochastic levels. Next, we evaluate the performance and distributional shift of a robust numeric verbalization prompt across single vs. two-step confidence elicitation procedure. We also compare the performance of the same prompt with different versions of GPT and different numerical scales. Finally, we combine the sample-based consistency and verbalized methods to propose a hybrid framework that yields a better uncertainty estimation for GPT models. Overall, our work proposes novel uncertainty quantification methods that will improve the reliability of Large Language Models in misinformation mitigation applications.</abstract>
<identifier type="citekey">rivera-etal-2024-combining</identifier>
<location>
<url>https://aclanthology.org/2024.uncertainlp-1.12</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>114</start>
<end>126</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation
%A Rivera, Mauricio
%A Godbout, Jean-François
%A Rabbany, Reihaneh
%A Pelrine, Kellin
%Y Vázquez, Raúl
%Y Celikkanat, Hande
%Y Ulmer, Dennis
%Y Tiedemann, Jörg
%Y Swayamdipta, Swabha
%Y Aziz, Wilker
%Y Plank, Barbara
%Y Baan, Joris
%Y de Marneffe, Marie-Catherine
%S Proceedings of the 1st Workshop on Uncertainty-Aware NLP (UncertaiNLP 2024)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St Julians, Malta
%F rivera-etal-2024-combining
%X Large Language Models have emerged as prime candidates to tackle misinformation mitigation. However, existing approaches struggle with hallucinations and overconfident predictions. We propose an uncertainty quantification framework that leverages both direct confidence elicitation and sampled-based consistency methods to provide better calibration for NLP misinformation mitigation solutions. We first investigate the calibration of sample-based consistency methods that exploit distinct features of consistency across sample sizes and stochastic levels. Next, we evaluate the performance and distributional shift of a robust numeric verbalization prompt across single vs. two-step confidence elicitation procedure. We also compare the performance of the same prompt with different versions of GPT and different numerical scales. Finally, we combine the sample-based consistency and verbalized methods to propose a hybrid framework that yields a better uncertainty estimation for GPT models. Overall, our work proposes novel uncertainty quantification methods that will improve the reliability of Large Language Models in misinformation mitigation applications.
%U https://aclanthology.org/2024.uncertainlp-1.12
%P 114-126
Markdown (Informal)
[Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation](https://aclanthology.org/2024.uncertainlp-1.12) (Rivera et al., UncertaiNLP-WS 2024)
ACL