None of the Above, Less of the Right: Parallel Patterns between Humans and LLMs on Multi-Choice Questions Answering Article Swipe

PDF

Zhi Rui Tam , Chunfei Wu , Chieh-Yen Lin , Yun-Nung Chen ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2503.01550

Multiple-choice exam questions with "None of the above" (NA) options have been extensively studied in educational testing, in which existing research suggests that they better assess true knowledge. However, their impact on Large Language Models (LLMs) evaluation remains underexplored. Through systematic experiments with 28 LLMs on the MMLU benchmark, we examine how NA options affect model performance and confidence calibration. Our analysis reveals that NA options, when used as the correct answer, lead to a consistent 30-50\% performance drop across models regardless of scale--suggesting that LLMs lack the meta-cognitive ability to systematically evaluate and reject all given options when none are correct. This degradation shows strong domain dependence, with minimal impact on mathematical reasoning (14.6\% drop) but severe effects on tasks requiring uncertainty handling like business ethics (48.1\% drop). Our results highlight important implications for benchmark design and raise questions about LLMs' ability to handle uncertainty in real-world applications.

Related Topics

And Then There Were None

Sixpence None The Richer

As Above, So Below (Film)

Less Than Zero (Film)

Less-Than Sign

Kiss Me (Sixpence None The Richer Song)

Above The Law (1988 Film)

Circling From Above

Above The Rim

And Then There Were None (Tv Series)

Death From Above 1979

And Then There Were None (1945 Film)

List Of Prominent Mountains Of The Alps Above 3000 M

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2503.01550
PDF: https://arxiv.org/pdf/2503.01550
OA Status: green
OpenAlex ID: https://openalex.org/W4415084990

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4415084990

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2503.01550

Digital Object Identifier
Title: None of the Above, Less of the Right: Parallel Patterns between Humans and LLMs on Multi-Choice Questions Answering

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-03-03

Full publication date if available
Authors: Zhi Rui Tam, Chunfei Wu, Chieh-Yen Lin, Yun-Nung Chen

List of authors in order
Landing page: https://arxiv.org/abs/2503.01550

Publisher landing page
PDF URL: https://arxiv.org/pdf/2503.01550

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2503.01550

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4415084990
doi	https://doi.org/10.48550/arxiv.2503.01550
ids.doi	https://doi.org/10.48550/arxiv.2503.01550
ids.openalex	https://openalex.org/W4415084990
fwci	0.0
type	preprint
title	None of the Above, Less of the Right: Parallel Patterns between Humans and LLMs on Multi-Choice Questions Answering
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T10028
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9847000241279602
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1702
topics[0].subfield.display_name	Artificial Intelligence
topics[0].display_name	Topic Modeling
topics[1].id	https://openalex.org/T10181
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9772999882698059
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1702
topics[1].subfield.display_name	Artificial Intelligence
topics[1].display_name	Natural Language Processing Techniques
topics[2].id	https://openalex.org/T13274
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.9477999806404114
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1710
topics[2].subfield.display_name	Information Systems
topics[2].display_name	Expert finding and Q&A systems
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2503.01550
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2503.01550
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2503.01550
locations[1].id	doi:10.48550/arxiv.2503.01550
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id	https://openalex.org/licenses/cc-by
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2503.01550
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5028150164
authorships[0].author.orcid	https://orcid.org/0000-0001-9968-2416
authorships[0].author.display_name	Zhi Rui Tam
authorships[0].author_position	first
authorships[0].raw_author_name	Tam, Zhi Rui
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5032589855
authorships[1].author.orcid	https://orcid.org/0000-0001-7961-1186
authorships[1].author.display_name	Chunfei Wu
authorships[1].author_position	middle
authorships[1].raw_author_name	Wu, Cheng-Kuang
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5012260456
authorships[2].author.orcid
authorships[2].author.display_name	Chieh-Yen Lin
authorships[2].author_position	middle
authorships[2].raw_author_name	Lin, Chieh-Yen
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5058211616
authorships[3].author.orcid
authorships[3].author.display_name	Yun-Nung Chen
authorships[3].author_position	last
authorships[3].raw_author_name	Chen, Yun-Nung
authorships[3].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2503.01550
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-12T00:00:00
display_name	None of the Above, Less of the Right: Parallel Patterns between Humans and LLMs on Multi-Choice Questions Answering
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T10028
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9847000241279602
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1702
primary_topic.subfield.display_name	Artificial Intelligence
primary_topic.display_name	Topic Modeling
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2503.01550
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2503.01550
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2503.01550
primary_location.id	pmh:oai:arXiv.org:2503.01550
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2503.01550
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2503.01550
publication_date	2025-03-03
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	74
abstract_inverted_index.28	43
abstract_inverted_index.NA	52, 64
abstract_inverted_index.as	68
abstract_inverted_index.in	14, 17, 146
abstract_inverted_index.of	5, 82
abstract_inverted_index.on	31, 45, 111, 119
abstract_inverted_index.to	73, 90, 143
abstract_inverted_index.we	49
abstract_inverted_index.Our	60, 129
abstract_inverted_index.all	95
abstract_inverted_index.and	57, 93, 137
abstract_inverted_index.are	100
abstract_inverted_index.but	116
abstract_inverted_index.for	134
abstract_inverted_index.how	51
abstract_inverted_index.the	6, 46, 69, 87
abstract_inverted_index.(NA)	8
abstract_inverted_index.LLMs	44, 85
abstract_inverted_index.MMLU	47
abstract_inverted_index.This	102
abstract_inverted_index.been	11
abstract_inverted_index.drop	78
abstract_inverted_index.exam	1
abstract_inverted_index.have	10
abstract_inverted_index.lack	86
abstract_inverted_index.lead	72
abstract_inverted_index.like	124
abstract_inverted_index.none	99
abstract_inverted_index.that	22, 63, 84
abstract_inverted_index.they	23
abstract_inverted_index.true	26
abstract_inverted_index.used	67
abstract_inverted_index.when	66, 98
abstract_inverted_index.with	3, 42, 108
abstract_inverted_index."None	4
abstract_inverted_index.LLMs'	141
abstract_inverted_index.Large	32
abstract_inverted_index.about	140
abstract_inverted_index.drop)	115
abstract_inverted_index.given	96
abstract_inverted_index.model	55
abstract_inverted_index.raise	138
abstract_inverted_index.shows	104
abstract_inverted_index.tasks	120
abstract_inverted_index.their	29
abstract_inverted_index.which	18
abstract_inverted_index.(LLMs)	35
abstract_inverted_index.Models	34
abstract_inverted_index.above"	7
abstract_inverted_index.across	79
abstract_inverted_index.affect	54
abstract_inverted_index.assess	25
abstract_inverted_index.better	24
abstract_inverted_index.design	136
abstract_inverted_index.domain	106
abstract_inverted_index.drop).	128
abstract_inverted_index.ethics	126
abstract_inverted_index.handle	144
abstract_inverted_index.impact	30, 110
abstract_inverted_index.models	80
abstract_inverted_index.reject	94
abstract_inverted_index.severe	117
abstract_inverted_index.strong	105
abstract_inverted_index.(14.6\%	114
abstract_inverted_index.(48.1\%	127
abstract_inverted_index.30-50\%	76
abstract_inverted_index.Through	39
abstract_inverted_index.ability	89, 142
abstract_inverted_index.answer,	71
abstract_inverted_index.correct	70
abstract_inverted_index.effects	118
abstract_inverted_index.examine	50
abstract_inverted_index.minimal	109
abstract_inverted_index.options	9, 53, 97
abstract_inverted_index.remains	37
abstract_inverted_index.results	130
abstract_inverted_index.reveals	62
abstract_inverted_index.studied	13
abstract_inverted_index.However,	28
abstract_inverted_index.Language	33
abstract_inverted_index.analysis	61
abstract_inverted_index.business	125
abstract_inverted_index.correct.	101
abstract_inverted_index.evaluate	92
abstract_inverted_index.existing	19
abstract_inverted_index.handling	123
abstract_inverted_index.options,	65
abstract_inverted_index.research	20
abstract_inverted_index.suggests	21
abstract_inverted_index.testing,	16
abstract_inverted_index.benchmark	135
abstract_inverted_index.highlight	131
abstract_inverted_index.important	132
abstract_inverted_index.questions	2, 139
abstract_inverted_index.reasoning	113
abstract_inverted_index.requiring	121
abstract_inverted_index.benchmark,	48
abstract_inverted_index.confidence	58
abstract_inverted_index.consistent	75
abstract_inverted_index.evaluation	36
abstract_inverted_index.knowledge.	27
abstract_inverted_index.real-world	147
abstract_inverted_index.regardless	81
abstract_inverted_index.systematic	40
abstract_inverted_index.degradation	103
abstract_inverted_index.dependence,	107
abstract_inverted_index.educational	15
abstract_inverted_index.experiments	41
abstract_inverted_index.extensively	12
abstract_inverted_index.performance	56, 77
abstract_inverted_index.uncertainty	122, 145
abstract_inverted_index.calibration.	59
abstract_inverted_index.implications	133
abstract_inverted_index.mathematical	112
abstract_inverted_index.applications.	148
abstract_inverted_index.meta-cognitive	88
abstract_inverted_index.systematically	91
abstract_inverted_index.underexplored.	38
abstract_inverted_index.Multiple-choice	0
abstract_inverted_index.scale--suggesting	83
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	4
citation_normalized_percentile