116 citations · 151 across the 8 of their papers we have counts for
10 papers · 1 filter
Personalized Alignment of Language Models with Human Value Profiles
Rashon Poole, Farnaz Jahanbakhsh
Large language models are increasingly used for subjective tasks such as seeking advice, where there is often no single correct answer. Yet dominant alignment methods learn a singl…
Value Faces: Surfacing How Self-Presentation Shifts Across Relationships
Gabriel Koo, Rayhan Rashed, Farnaz Jahanbakhsh
People present different aspects of themselves across relationships. Computational work has captured such variation in communication style. But this variation also extends to which…
Interpretive Cultures: Resonance, randomness, and negotiated meaning for AI-assisted tarot divination
Matthew Prock, Ziv Epstein, Hope Schroeder +4
While generative AI tools are increasingly adopted for creative and analytical tasks, their role in interpretive practices, where meaning is subjective, plural, and non-causal, rem…
Persuasion in Online Conversations Is Associated with Alignment in Expressed Human Values
Bhavesh Vuyyuru, Farnaz Jahanbakhsh
Online disagreements often fail to produce understanding, instead reinforcing existing positions or escalating conflict. Prior work on predictors of successful persuasion in online…
What If Moderation Didn't Mean Suppression? A Case for Personalized Content Transformation
Rayhan Rashed, Farnaz Jahanbakhsh
Centralized content moderation paradigm both falls short and over-reaches: 1) it fails to account for the subjective nature of harm, and 2) it acts with blunt suppression in respon…
Value Alignment of Social Media Ranking Algorithms
Farnaz Jahanbakhsh, Dora Zhao, Tiziano Piccardi +4
While social media feed rankings are primarily driven by engagement signals rather than any explicit value system, the resulting algorithmic feeds are not value-neutral: engagement…
Alexandria: A Library of Pluralistic Values for Realtime Re-Ranking of Social Media Feeds
Akaash Kolluri, Renn Su, Farnaz Jahanbakhsh +3
Social media feed ranking algorithms fail when they too narrowly focus on engagement as their objective. The literature has asserted a wide variety of values that these algorithms…
A Browser Extension for in-place Signaling and Assessment of Misinformation
Farnaz Jahanbakhsh, David R. Karger
The status-quo of misinformation moderation is a central authority, usually social platforms, deciding what content constitutes misinformation and how it should be handled. However…
Understanding Questions that Arise When Working with Business Documents
Farnaz Jahanbakhsh, Elnaz Nouri, Robert Sim +2
While digital assistants are increasingly used to help with various productivity tasks, less attention has been paid to employing them in the domain of business documents. To build…
Exploring Lightweight Interventions at Posting Time to Reduce the Sharing of Misinformation on Social Media
Farnaz Jahanbakhsh, Amy X. Zhang, Adam J. Berinsky +3
When users on social media share content without considering its veracity, they may unwittingly be spreading misinformation. In this work, we investigate the design of lightweight…