@inproceedings{falk-lapesa-2025-mining,
title = "Mining the uncertainty patterns of humans and models in the annotation of moral foundations and human values",
author = "Falk, Neele and
Lapesa, Gabriella",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1116/",
doi = "10.18653/v1/2025.acl-long.1116",
pages = "22898--22921",
ISBN = "979-8-89176-251-0",
abstract = "The NLP community has converged on considering disagreement in annotation (or human label variation, HLV) as a constitutive feature of subjective tasks. This paper makes a further step by investigating the relationship between HLV and model uncertainty, and the impact of linguistic features of the items on both. We focus on the identification of moral foundations (e.g., care, fairness, loyalty) and human values (e.g., be polite, be honest) in text. We select three standard datasets and proceed into two steps. First, we focus on HLV and analyze the linguistic features (complexity, polarity, pragmatic phenomena, lexical choices) that correlate with HLV. Next, we proceed to uncertainty and its relationship to HLV. We experiment with RoBERTa and Flan-T5 in a number of training setups and evaluation metrics that test the calibration of uncertainty to HLV and its relationship to performance beyond majority vote; next, we analyze the impact of linguistic features on uncertainty. We find that RoBERTa with soft loss is better calibrated to HLV, and we find alignment between calibrated models and humans in the features (textual complexity and polarity) triggering variation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="falk-lapesa-2025-mining">
<titleInfo>
<title>Mining the uncertainty patterns of humans and models in the annotation of moral foundations and human values</title>
</titleInfo>
<name type="personal">
<namePart type="given">Neele</namePart>
<namePart type="family">Falk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriella</namePart>
<namePart type="family">Lapesa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>The NLP community has converged on considering disagreement in annotation (or human label variation, HLV) as a constitutive feature of subjective tasks. This paper makes a further step by investigating the relationship between HLV and model uncertainty, and the impact of linguistic features of the items on both. We focus on the identification of moral foundations (e.g., care, fairness, loyalty) and human values (e.g., be polite, be honest) in text. We select three standard datasets and proceed into two steps. First, we focus on HLV and analyze the linguistic features (complexity, polarity, pragmatic phenomena, lexical choices) that correlate with HLV. Next, we proceed to uncertainty and its relationship to HLV. We experiment with RoBERTa and Flan-T5 in a number of training setups and evaluation metrics that test the calibration of uncertainty to HLV and its relationship to performance beyond majority vote; next, we analyze the impact of linguistic features on uncertainty. We find that RoBERTa with soft loss is better calibrated to HLV, and we find alignment between calibrated models and humans in the features (textual complexity and polarity) triggering variation.</abstract>
<identifier type="citekey">falk-lapesa-2025-mining</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1116</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1116/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>22898</start>
<end>22921</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mining the uncertainty patterns of humans and models in the annotation of moral foundations and human values
%A Falk, Neele
%A Lapesa, Gabriella
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F falk-lapesa-2025-mining
%X The NLP community has converged on considering disagreement in annotation (or human label variation, HLV) as a constitutive feature of subjective tasks. This paper makes a further step by investigating the relationship between HLV and model uncertainty, and the impact of linguistic features of the items on both. We focus on the identification of moral foundations (e.g., care, fairness, loyalty) and human values (e.g., be polite, be honest) in text. We select three standard datasets and proceed into two steps. First, we focus on HLV and analyze the linguistic features (complexity, polarity, pragmatic phenomena, lexical choices) that correlate with HLV. Next, we proceed to uncertainty and its relationship to HLV. We experiment with RoBERTa and Flan-T5 in a number of training setups and evaluation metrics that test the calibration of uncertainty to HLV and its relationship to performance beyond majority vote; next, we analyze the impact of linguistic features on uncertainty. We find that RoBERTa with soft loss is better calibrated to HLV, and we find alignment between calibrated models and humans in the features (textual complexity and polarity) triggering variation.
%R 10.18653/v1/2025.acl-long.1116
%U https://aclanthology.org/2025.acl-long.1116/
%U https://doi.org/10.18653/v1/2025.acl-long.1116
%P 22898-22921
Markdown (Informal)
[Mining the uncertainty patterns of humans and models in the annotation of moral foundations and human values](https://aclanthology.org/2025.acl-long.1116/) (Falk & Lapesa, ACL 2025)
ACL