大模型
arxiv.org ·
告诉我为什么、何时以及如何：人格、证据与语境对老年人感知对话式 AI 解释的影响
该 arXiv 论文（cs.HC）研究基于大模型的语音助手（LLM-VA）在居家养老场景中的解释设计。作者对 140 名老年人开展混合设计实验，考察两个维度：解释的证据来源（evidential grounding）与语音助手的对话人格（宜人性、外向性），并覆盖两种使用语境。结果显示两个维度以不同但相互依赖的方式影响老年人的感知，说明单一化的解释策略并不适用。作者据此提出协调解释内容、对话表达方式与使用语境的设计建议。
AI推荐理由 arXiv 正式论文（cs.HC，v3），有明确研究设计：140 名老年人混合设计实验，考察证据来源（evidential grounding）与语音助手对话人格（agreeableness、extraversion）两个维度对解释感知的影响，结论是两维度作用不同且相互依赖，反对一刀切解释策略。属可验证的学术证据，信息密度中等。局限：仅摘要可见，无具体效应量与统计细节；主题聚焦老年人 LLM 语音助手可解释性，对通用 AI/模型/Agent 开发的直接迁移价值有限，故兴趣分中等。
62
正文
Computer Science > Human-Computer Interaction
arXiv:2603.08164 (cs)
[Submitted on 9 Mar 2026 (v1), last revised 21 Sep 2026 (this version, v3)]
Title:Tell Me Why, When, and How: Effects of Personality, Evidence, and Context on Older Adults' Perceptions of Conversational AI Explanations
Authors:Niharika Mathur, Hasibur Rahman, Smit Desai
View a PDF of the paper titled Tell Me Why, When, and How: Effects of Personality, Evidence, and Context on Older Adults' Perceptions of Conversational AI Explanations, by Niharika Mathur and 2 other authors
View PDF
HTML (experimental)
Abstract:Large Language Model-based voice assistants (LLM-VAs) have shown potential to support older adults aging in place through proactive reminders, health information, and everyday assistance. As LLM-VAs become more conversational, designing explanations of their behavior requires understanding what information they communicate and how they deliver it. While prior work has studied older adults' explainability requirements, relatively little is known about their perceptions of explanations when an LLM-VA's conversational personality varies. To address this gap, we conducted a mixed-design study with 140 older adults, examining two dimensions of explanation design: evidential grounding (source of information) and the VA's conversational personality (agreeableness and extraversion), across two contexts of use. Our results show that both dimensions influenced older adults' perceptions in distinct but interdependent ways, challenging one-size-fits-all explanation strategies. We conclude with practical design implications for coordinating explanation content, conversational delivery, and context in future LLM-VAs supporting aging in place.
Subjects:
Human-Computer Interaction (cs.HC)
Cite as:
arXiv:2603.08164 [cs.HC]
(or
arXiv:2603.08164v3 [cs.HC] for this version)
https://doi.org/10.48550/arXiv.2603.08164
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Hasibur Rahman [view email]
[v1]
Mon, 9 Mar 2026 09:44:13 UTC (17,069 KB)
[v2]
Wed, 29 Apr 2026 01:58:12 UTC (17,043 KB)
[v3]
Mon, 21 Sep 2026 14:58:19 UTC (12,843 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Tell Me Why, When, and How: Effects of Personality, Evidence, and Context on Older Adults' Perceptions of Conversational AI Explanations, by Niharika Mathur and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.HC
new
|
recent
| 2026-03
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)