Back
2024 study at the CHI Conference
webdl.acm.org·dl.acm.org/doi/10.1145/3613904.3642459
A peer-reviewed CHI 2024 paper providing empirical user research on AI honesty and truthfulness perception, relevant to alignment researchers studying how truthfulness failures manifest in real-world human-AI interaction.
Metadata
Importance: 45/100conference paperprimary source
Summary
A 2024 CHI Conference study examining how users perceive and evaluate honesty and truthfulness in conversational AI systems, exploring the gap between user expectations and actual AI behavior. The research investigates how deceptive or misleading AI outputs affect user trust and experience. Findings likely inform design guidelines for more transparent and trustworthy AI interfaces.
Key Points
- •Examines user mental models around AI honesty and how people assess whether an AI is being truthful or deceptive
- •Investigates the impact of AI truthfulness failures on user trust and willingness to rely on AI systems
- •Presented at CHI 2024, a top-tier human-computer interaction venue, lending methodological credibility
- •Bridges alignment concerns (truthfulness) with practical UX implications for deployed AI systems
- •Provides empirical grounding for design recommendations around transparent and honest AI communication
Cited by 1 page
| Page | Type | Quality |
|---|---|---|
| Epistemic Sycophancy | Risk | 60.0 |
Cached Content Preview
HTTP 200Fetched Apr 9, 202698 KB
Generative Echo Chamber? Effect of LLM-Powered Search Systems on Diverse Information Seeking | Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems
chi;taxonomy:taxonomy:conference-collections;article:article:doi\:10.1145/3613904.3642459;wgroup:string:ACM Publication Websites;groupTopic:topic:acm-pubtype>proceeding;ctype:string:Book Content;subPage:string:Full Text;issue:issue:doi\:10.1145/3613904;page:string:Article/Chapter View;csubtype:string:Conference Proceedings;website:website:dl-site;journal:journal:acmconferences;pageGroup:string:Publication Pages">
Jun
JUL
Aug
20
2024
2025
2026
success
fail
About this capture
COLLECTED BY
Collection: GDELT Project
TIMESTAMPS
The Wayback Machine - http://web.archive.org/web/20250720100445/https://dl.acm.org/doi/10.1145/3613904.3642459
skip to main content
Advanced Search
Browse
About
Sign in
Register
Advanced Search
Journals
Magazines
Proceedings
Books
SIGs
Conferences
People
More
Search ACM Digital Library
SearchSearch
Advanced Search
10.1145/3613904.3642459acmconferencesArticle/Chapter ViewFull TextPublication PageschiConference Proceedingsconference-collections
chi
Conference
Proceedings
Upcoming Events
Authors
Affiliations
Award Winners
More
Home
Browse Publications
chi
ACM Conferences
CHI '24
Generative Echo Chamber? Effect of LLM-Powered Search Systems on Diverse Information Seeking
Export Citations
Select Citation formatBibTeXEndNoteACM Ref
Please download or close your previous search result export first before starting a new bulk export.
Preview is not available.
By clicking download,a status dialog will open to start the export process. The process may takea few minutes but once it finishes a file will be downloadable from your browser. You may continue to browse the DL while the export process is in progress.
Download citation
Copy citation
Home
Conferences
CHI
Proceedings
CHI '24
Generative Echo Chamber? Effect of LLM-Powered Search Systems on Diverse Information Seeking
research-article
Open access
Share on
Generative Echo Chamber? Effect of LLM-Powered Search Systems on Diverse Information Seeking
Authors: Nikhil Sharma, Q. Vera Liao, Ziang XiaoAuthors Info & Claims
C
... (truncated, 98 KB total)Resource ID:
b7b6e436dc9cbce9 | Stable ID: sid_KdcKzYJ5QA