@inproceedings{gor-etal-2026-ai,
title = "{AI}, Take the Wheel: What Drives Delegation and Trust in Human{--}Computer Cooperative Question Answering?",
author = "Gor, Maharshi and
Sung, Yoo Yeon and
Hou, Yu and
Fleisig, Eve and
Ying, Zhu Irene and
Zhou, Tianyi and
Boyd-Graber, Jordan Lee",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.422/",
pages = "8664--8689",
ISBN = "979-8-89176-395-1",
abstract = "AI systems are fallible, and humans can make mistakes in deciding whether to trustAI over their own judgment. Thus, improving human-AI collaboration requires that we understand when,why, and how humans decide to rely on AI. We study two reliance decisions: delegating a task toAI without seeing its output (whether AI is used) and evaluating AI suggestions to decidewhether to adopt them how AI output shapes final decisions).Both matter for effective collaboration, yet prior work lacks naturalistic experiments capturing both patternsfor the same users. We address this gap by studying collaborative human{--}AI teams competing in aquestion-answering game in which humans can choose when and how to work with AI agents to win.Our 24 matches pair 23 expert humans with 16 AI agents, capturing 387 delegation and 1440 adoption decisions.While human{--}AI collaboration performs better than either AI or humansalone, humans make suboptimal collaboration decisions, bothunder-relying on correct AI suggestions (3.7{\%} of opportunities missed) and over-relying when AI misleads them (1.5{\%}).Both parties contribute wrong answers: reported model confidence is near chance when humans and AI disagree, while confirmation bias drives higher under-reliance (60.7{\%}) when an AI suggestion agrees with humans' initial incorrect answer."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gor-etal-2026-ai">
<titleInfo>
<title>AI, Take the Wheel: What Drives Delegation and Trust in Human–Computer Cooperative Question Answering?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maharshi</namePart>
<namePart type="family">Gor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoo</namePart>
<namePart type="given">Yeon</namePart>
<namePart type="family">Sung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eve</namePart>
<namePart type="family">Fleisig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhu</namePart>
<namePart type="given">Irene</namePart>
<namePart type="family">Ying</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyi</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="given">Lee</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>AI systems are fallible, and humans can make mistakes in deciding whether to trustAI over their own judgment. Thus, improving human-AI collaboration requires that we understand when,why, and how humans decide to rely on AI. We study two reliance decisions: delegating a task toAI without seeing its output (whether AI is used) and evaluating AI suggestions to decidewhether to adopt them how AI output shapes final decisions).Both matter for effective collaboration, yet prior work lacks naturalistic experiments capturing both patternsfor the same users. We address this gap by studying collaborative human–AI teams competing in aquestion-answering game in which humans can choose when and how to work with AI agents to win.Our 24 matches pair 23 expert humans with 16 AI agents, capturing 387 delegation and 1440 adoption decisions.While human–AI collaboration performs better than either AI or humansalone, humans make suboptimal collaboration decisions, bothunder-relying on correct AI suggestions (3.7% of opportunities missed) and over-relying when AI misleads them (1.5%).Both parties contribute wrong answers: reported model confidence is near chance when humans and AI disagree, while confirmation bias drives higher under-reliance (60.7%) when an AI suggestion agrees with humans’ initial incorrect answer.</abstract>
<identifier type="citekey">gor-etal-2026-ai</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.422/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>8664</start>
<end>8689</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AI, Take the Wheel: What Drives Delegation and Trust in Human–Computer Cooperative Question Answering?
%A Gor, Maharshi
%A Sung, Yoo Yeon
%A Hou, Yu
%A Fleisig, Eve
%A Ying, Zhu Irene
%A Zhou, Tianyi
%A Boyd-Graber, Jordan Lee
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F gor-etal-2026-ai
%X AI systems are fallible, and humans can make mistakes in deciding whether to trustAI over their own judgment. Thus, improving human-AI collaboration requires that we understand when,why, and how humans decide to rely on AI. We study two reliance decisions: delegating a task toAI without seeing its output (whether AI is used) and evaluating AI suggestions to decidewhether to adopt them how AI output shapes final decisions).Both matter for effective collaboration, yet prior work lacks naturalistic experiments capturing both patternsfor the same users. We address this gap by studying collaborative human–AI teams competing in aquestion-answering game in which humans can choose when and how to work with AI agents to win.Our 24 matches pair 23 expert humans with 16 AI agents, capturing 387 delegation and 1440 adoption decisions.While human–AI collaboration performs better than either AI or humansalone, humans make suboptimal collaboration decisions, bothunder-relying on correct AI suggestions (3.7% of opportunities missed) and over-relying when AI misleads them (1.5%).Both parties contribute wrong answers: reported model confidence is near chance when humans and AI disagree, while confirmation bias drives higher under-reliance (60.7%) when an AI suggestion agrees with humans’ initial incorrect answer.
%U https://aclanthology.org/2026.findings-acl.422/
%P 8664-8689
Markdown (Informal)
[AI, Take the Wheel: What Drives Delegation and Trust in Human–Computer Cooperative Question Answering?](https://aclanthology.org/2026.findings-acl.422/) (Gor et al., Findings 2026)
ACL
- Maharshi Gor, Yoo Yeon Sung, Yu Hou, Eve Fleisig, Zhu Irene Ying, Tianyi Zhou, and Jordan Lee Boyd-Graber. 2026. AI, Take the Wheel: What Drives Delegation and Trust in Human–Computer Cooperative Question Answering?. In Findings of the Association for Computational Linguistics: ACL 2026, pages 8664–8689, San Diego, California, United States. Association for Computational Linguistics.