Personalized Alignment of Language Models with Human Value Profiles

Rashon Poole, Farnaz Jahanbakhsh

EMNLP 2026 (Main)

Value misalignment in X’s feed algorithm is a reflection of value tensions in engagement

Ziv Epstein, Farnaz Jahanbakhsh, Tiziano Piccardi, Alex Peytavin, Isabel Gallegos, Shardul Sapkota, Dora Zhao, Johan Ugander, Michael Bernstein

PNAS 2026 (Brief Report)

Paper

Coverage:The ConversationStanford ReportStanford HAI News404 Media

Value Alignment of Social Media Ranking Algorithms

Farnaz Jahanbakhsh*, Dora Zhao*, Tiziano Piccardi, Zachary Robertson, Ziv Epstein, Sanmi Koyejo, Michael Bernstein

CHI 2026

Paper · Project Site

Coverage:FOOM — Independent reporting from the edge of AI science

What If Moderation Didn't Mean Suppression? A Case for Personalized Content Transformation

Rayhan Rashed, Farnaz Jahanbakhsh

CHI 2026 Best Paper Honorable Mention

Paper · Code · Project Site

Coverage:University of Michigan CSE News

Interpretive Cultures: Resonance, Randomness and Negotiated Meaning for AI-Assisted Tarot Divination

Matthew Kieran Prock*, Ziv Epstein*, Hope Schroeder, Amy Smith, Cassandra Lee, Vana Goblot, Farnaz Jahanbakhsh

CHI 2026

Paper

Coverage:PBS NewsYahoo! NewsFortuneThe ConversationVice

Whose Values? Measuring the (Subjective) Expression of Basic Human Values in Social Media Posts

Ziv Epstein, Farnaz Jahanbakhsh, Tiziano Piccardi, Isabel Gallegos, Dora Zhao, Johan Ugander, Michael Bernstein

ICWSM 2026

Paper

Alexandria: A Library of Pluralistic Values for Realtime Re-Ranking of Social Media Feeds

Akaash Kolluri*, Renn Su*, Farnaz Jahanbakhsh, Dora Zhao, Tiziano Piccardi, Michael S. Bernstein

ICWSM 2026

Paper

A Browser Extension for In-Place Signaling and Assessment of Misinformation

Farnaz Jahanbakhsh, David R. Karger

CHI 2024

Paper · Code

Coverage:MIT Technology ReviewMIT NewsThe Hindu

Exploring the Use of Personalized AI for Identifying Misinformation on Social Media

Farnaz Jahanbakhsh, Yannis Katsis, Dakuo Wang, Lucian Popa, Michael Muller

CHI 2023

Paper · Code · Code

Understanding Questions that Arise When Working with Business Documents

Farnaz Jahanbakhsh, Elnaz Nouri, Robert Sim, Ryen W. White, Adam Fourney

CSCW 2022

Paper

Designs for Directing Students' Attention in a Large-Scale Classroom Social Annotation Platform

Jumana Almahmoud, Farnaz Jahanbakhsh, Marc Facciotti, Michele Igo, Kamali Spirathi, Kobi Gal, David R. Karger

CSCW 2022

Paper

Leveraging Structured Trusted-Peer Assessments to Combat Misinformation

Farnaz Jahanbakhsh, Amy X. Zhang, David R. Karger

CSCW 2022

Paper · Code · Code

Coverage:Big ThinkTN (Todo Noticias — Argentina)MIT News

Our Browser Extension Lets Readers Change the Headlines on News Articles, and You Won't Believe What They Did!

Farnaz Jahanbakhsh, Amy X. Zhang, Karrie Karahalios, David R. Karger

CSCW 2022

Paper · Code · Code

Exploring Lightweight Interventions at Posting Time to Reduce the Sharing of Misinformation on Social Media

Farnaz Jahanbakhsh, Gordon Pennycook, David G. Rand, Adam Berinsky, Amy X. Zhang, David R. Karger

CSCW 2021

Paper

An Experimental Study of Bias in Platform Worker Ratings: The Role of Performance Quality and Gender

Farnaz Jahanbakhsh, Justin Cranshaw, Scott Counts, Walter Lasecki, Kori Inkpen

CHI 2020

Paper

Effects of Past Interactions on User Experience with Recommended Documents

Farnaz Jahanbakhsh, Ahmed Hassan Awadallah, Susan T. Dumais, Xuhai Xu

CHIIR 2020

Paper

Structure or Nurture? The Effects of Team-Building Activities and Team Composition on Team Outcomes

Emily Hastings*, Farnaz Jahanbakhsh*, Karrie Karahalios, Darko Marinov, Brian Bailey

CSCW 2018

Paper

You Want Me to Work with Who? Stakeholder Perceptions of Automated Team Formation in Project-based Courses

Farnaz Jahanbakhsh, Wai-Tat Fu, Karrie Karahalios, Darko Marinov, Brian Bailey

CHI 2017 Best Paper Award

Paper