LLMs in social services: How does chatbot accuracy affect human accuracy?

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Gosciak, Jennah, Giannella, Eric, Guo, Zhaowen, Chen, Michael, Koenecke, Allison
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Human-Computer Interaction Computers and Society
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

A Critical Pragmatism Approach for Algorithmic Fairness: Lessons from Urban Planning Theory
von: Gosciak, Jennah, et al.
Veröffentlicht: (2026)

How much does context affect the accuracy of AI health advice?
von: Garg, Prashant, et al.
Veröffentlicht: (2025)

Scrutinizing Index-Based Risk Assessments: A Case Study in NYC Decision-making for Heat Emergency Management
von: Gosciak, Jennah, et al.
Veröffentlicht: (2026)

Fairness-in-the-Workflow: How Machine Learning Practitioners at Big Tech Companies Approach Fairness in Recommender Systems
von: Yan, Jing Nathan, et al.
Veröffentlicht: (2025)

AI-Enabled grading with near-domain data for scaling feedback with human-level accuracy
von: Agarwal, Shyam, et al.
Veröffentlicht: (2025)

(Un)fair devices: Moving beyond AI accuracy in personal sensing
von: Yfantidou, Sofia, et al.
Veröffentlicht: (2023)

How should my chatbot interact? A survey on human-chatbot interaction design
von: Chaves, Ana Paula, et al.
Veröffentlicht: (2019)

Will you donate money to a chatbot? The effect of chatbot anthropomorphic features and persuasion strategies on willingness to donate
von: Novozhilova, Ekaterina, et al.
Veröffentlicht: (2024)

ELIZA Reinterpreted: The world's first chatbot was not intended as a chatbot at all
von: Shrager, Jeff
Veröffentlicht: (2024)

Habit Coach: Customising RAG-based chatbots to support behavior change
von: Arabi, Arian Fooroogh Mand, et al.
Veröffentlicht: (2024)

People over trust AI-generated medical responses and view them to be as valid as doctors, despite low accuracy
von: Shekar, Shruthi, et al.
Veröffentlicht: (2024)

Allowing humans to interactively guide machines where to look does not always improve human-AI team's classification accuracy
von: Nguyen, Giang, et al.
Veröffentlicht: (2024)

Beyond AI advice -- independent aggregation boosts human-AI accuracy
von: Berger, Julian, et al.
Veröffentlicht: (2026)

Bias Delayed is Bias Denied? Assessing the Effect of Reporting Delays on Disparity Assessments
von: Gosciak, Jennah, et al.
Veröffentlicht: (2025)

From chalkboards to chatbots: SELAR assists teachers in embracing AI in the curriculum
von: Alers, Hani, et al.
Veröffentlicht: (2024)

Taming Toxic Talk: Using chatbots to intervene with users posting toxic comments
von: Foote, Jeremy, et al.
Veröffentlicht: (2026)

Unimib Assistant: designing a student-friendly RAG-based chatbot for all their needs
von: Antico, Chiara, et al.
Veröffentlicht: (2024)

The Sociotechnical Stack: Opportunities for Social Computing Research in Non-consensual Intimate Media
von: Qiwei, Li, et al.
Veröffentlicht: (2024)

From Script to Stage: Automating Experimental Design for Social Simulations with LLMs
von: Guo, Yuwei, et al.
Veröffentlicht: (2025)

How do datasets, developers, and models affect biases in a low-resourced language?: The Case of the Bengali Language
von: Das, Dipto, et al.
Veröffentlicht: (2025)

Platforms as Crime Scene, Judge, and Jury: How Victim-Survivors of Non-Consensual Intimate Imagery Report Abuse Online
von: Qiwei, Li, et al.
Veröffentlicht: (2025)

Invisible Saboteurs: Sycophantic LLMs Mislead Novices in Problem-Solving Tasks
von: Bo, Jessica Y., et al.
Veröffentlicht: (2025)

What is the role of human decisions in a world of artificial intelligence: an economic evaluation of human-AI collaboration in diabetic retinopathy screening
von: Wang, Yueye, et al.
Veröffentlicht: (2025)

Cognitive offloading and the speedup illusion in human-AI interaction
von: Yu, Sunny, et al.
Veröffentlicht: (2026)

Seeing Like an AI: How LLMs Apply (and Misapply) Wikipedia Neutrality Norms
von: Ashkinaze, Joshua, et al.
Veröffentlicht: (2024)

Generative AI as a Learning Buddy and Teaching Assistant: Pre-service Teachers' Uses and Attitudes
von: Nyaaba, Matthew, et al.
Veröffentlicht: (2024)

How does a spontaneously speaking conversational agent affect user behavior?
von: Iizuka, Takahisa, et al.
Veröffentlicht: (2022)

Cognitive AI framework 2.0: advances in the simulation of human thought
von: Salas-Guerra, Rommel
Veröffentlicht: (2025)

Bodioid: philosophical reflections on the hybrid of bodies and artefacts towards post-human
von: Xu, Jiang, et al.
Veröffentlicht: (2024)

Impacts of aspect ratio on task accuracy in parallel coordinates
von: Garner, Hugh, et al.
Veröffentlicht: (2024)

How Generative AI Empowers Attackers and Defenders Across the Trust & Safety Landscape
von: Kelley, Patrick Gage, et al.
Veröffentlicht: (2025)

Exploring LLMs for Automated Generation and Adaptation of Questionnaires
von: Adhikari, Divya Mani, et al.
Veröffentlicht: (2025)

What's it like to be a chat? On the co-simulation of artificial minds in human-AI conversations
von: Keeling, Geoff, et al.
Veröffentlicht: (2026)

A risk model and analysis method for the psychological safety of human and autonomous vehicles interaction
von: Sirgabsou, Yandika, et al.
Veröffentlicht: (2024)

The Promises and Perils of using LLMs for Effective Public Services
von: Moon, Erina Seh-Young, et al.
Veröffentlicht: (2026)

Facilitating the Integration of LLMs Into Online Experiments With Simple Chat
von: Schettino, R. Bermudez, et al.
Veröffentlicht: (2025)

Who Decides How Knowing Becomes Doing? Redistributing Authority in Human-AI Music Co-Creation
von: Hu, Zhejing, et al.
Veröffentlicht: (2025)

How Warm-Glow Alters the Usability of Technology
von: Saravanos, Antonios
Veröffentlicht: (2025)

Who Changed the Destiny of Rural Students, and How?: Unpacking ICT-Mediated Remote Education in Rural China
von: Sun, Yuling, et al.
Veröffentlicht: (2024)

LLMs Homogenize Values in Constructive Arguments on Value-Laden Topics
von: Shahid, Farhana, et al.
Veröffentlicht: (2025)