Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Magy Seif
Computer Science > Computation and Language
Large language models (LLMs) are increasingly used for emotional support, raising concern that sustained use may draw users away from their real-world relationships. Yet existing evaluations primarily focus on the safety, empathy, or helpfulness of responses, leaving under-examined a relational question: where does the model orient the user for continued support?
Computer Science > Human-Computer Interaction
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.
Computer Science > Machine Learning
While existing data attribution methods can identify which training examples build specific mechanistic circuits, they cannot explain how training data shapes the high-level behavioral decisions a model learns to make. To bridge this gap, we introduce Symbolic Mechanistic Data Attribution (SMDA), a framework that attributes training pairs to the interpretable symbolic policies governing model behavior.
Computer Science > Human-Computer Interaction
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.
Computer Science > Human-Computer Interaction
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.
[2510.05378] What Do You Mean? Exploring How Humans and AI Interact with Symbols and Meanings in Their Interactions
arXiv:2510.05378 (cs) View PDF HTML (experimental) Comments: Subjects: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) Cite as: arXiv:2510.05378 [cs.AI] (or arXiv:2510.05378v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2510.05378 Submission history From: Reza Habibi [ view email] [v1] Mon, 6 Oct 2025 21:13:22 UTC (3,040 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Connected Papers Toggle Connected Papers (What is Connected...
Talk, Listen, Connect: How Humans and AI Evaluate Empathy in Responses to Emotionally Charged Narratives
[Submitted on 23 Sep 2024 ( v1 ), last revised 2 Sep 2025 (this version, v2)] Title:Talk, Listen, Connect: How Humans and AI Evaluate Empathy in Responses to Emotionally Charged Narratives View a PDF of the paper titled Talk, Listen, Connect: How Humans and AI Evaluate Empathy in Responses to Emotionally Charged Narratives, by Mahnaz Roshanaei and 2 other authors View PDF HTML (experimental) Abstract:Social interactions promote well-being, yet barriers like geographic distance, time...
Info Overload: A Cooperative Evacuation Game
arXiv:2407.09559 (cs) View PDF HTML (experimental) Comments: Subjects: Human-Computer Interaction (cs.HC); Computer Science and Game Theory (cs.GT) Cite as: arXiv:2407.09559 [cs.HC] (or arXiv:2407.09559v1 [cs.HC] for this version) https://doi.org/10.48550/arXiv.2407.09559 Submission history From: Mj Johns [ view email] [v1] Sun, 30 Jun 2024 23:45:06 UTC (844 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Litmaps Toggle Litmaps (What is Litmaps?) scite.ai...
[2308.14224] Modeling Player Personality Factors from In-Game Behavior and Affective Expression
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.
On Video Game Balancing: Joining Player- and Data-Driven Analytics
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.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Magy
Contact Magy, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack