<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ranaldi-zanzotto-2024-hans">
    <titleInfo>
        <title>HANS, are you clever? Clever Hans Effect Analysis of Neural Systems</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Leonardo</namePart>
        <namePart type="family">Ranaldi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fabio</namePart>
        <namePart type="family">Zanzotto</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Danushka</namePart>
            <namePart type="family">Bollegala</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vered</namePart>
            <namePart type="family">Shwartz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Mexico City, Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Large Language Models (LLMs) have been exhibiting outstanding abilities to reason around cognitive states, intentions, and reactions of all people involved, letting humans guide and comprehend day-to-day social interactions effectively. In fact, several multiple-choice questions (MCQ) benchmarks have been proposed to construct solid assessments of the models’ abilities. However, earlier works demonstrate the presence of inherent “order bias” in LLMs, posing challenges to the appropriate evaluation. In this paper, we investigate LLMs’ resilience abilities through a series of probing tests using four MCQ benchmarks. Introducing adversarial examples, we show a significant performance gap, mainly when varying the order of the choices, which reveals a selection bias and brings into discussion reasoning abilities. Following a correlation between first positions and model choices due to positional bias, we hypothesized the presence of structural heuristics in the decision-making process of the LLMs, strengthened by including significant examples in few-shot scenarios. Finally, by using the Chain-of-Thought (CoT) technique, we elicit the model to reason and mitigate the bias by obtaining more robust models.</abstract>
    <identifier type="citekey">ranaldi-zanzotto-2024-hans</identifier>
    <identifier type="doi">10.18653/v1/2024.starsem-1.25</identifier>
    <location>
        <url>https://aclanthology.org/2024.starsem-1.25/</url>
    </location>
    <part>
        <date>2024-06</date>
        <extent unit="page">
            <start>314</start>
            <end>325</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T HANS, are you clever? Clever Hans Effect Analysis of Neural Systems
%A Ranaldi, Leonardo
%A Zanzotto, Fabio
%Y Bollegala, Danushka
%Y Shwartz, Vered
%S Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F ranaldi-zanzotto-2024-hans
%X Large Language Models (LLMs) have been exhibiting outstanding abilities to reason around cognitive states, intentions, and reactions of all people involved, letting humans guide and comprehend day-to-day social interactions effectively. In fact, several multiple-choice questions (MCQ) benchmarks have been proposed to construct solid assessments of the models’ abilities. However, earlier works demonstrate the presence of inherent “order bias” in LLMs, posing challenges to the appropriate evaluation. In this paper, we investigate LLMs’ resilience abilities through a series of probing tests using four MCQ benchmarks. Introducing adversarial examples, we show a significant performance gap, mainly when varying the order of the choices, which reveals a selection bias and brings into discussion reasoning abilities. Following a correlation between first positions and model choices due to positional bias, we hypothesized the presence of structural heuristics in the decision-making process of the LLMs, strengthened by including significant examples in few-shot scenarios. Finally, by using the Chain-of-Thought (CoT) technique, we elicit the model to reason and mitigate the bias by obtaining more robust models.
%R 10.18653/v1/2024.starsem-1.25
%U https://aclanthology.org/2024.starsem-1.25/
%U https://doi.org/10.18653/v1/2024.starsem-1.25
%P 314-325

Markdown (Informal)

[HANS, are you clever? Clever Hans Effect Analysis of Neural Systems](https://aclanthology.org/2024.starsem-1.25/) (Ranaldi & Zanzotto, *SEM 2024)

• HANS, are you clever? Clever Hans Effect Analysis of Neural Systems (Ranaldi & Zanzotto, *SEM 2024)

ACL

• Leonardo Ranaldi and Fabio Zanzotto. 2024. HANS, are you clever? Clever Hans Effect Analysis of Neural Systems. In Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024), pages 314–325, Mexico City, Mexico. Association for Computational Linguistics.