Zobrazeno 1 - 10
of 1 474
pro vyhledávání: '"A BERNSTEIN, MICHAEL"'
Autor:
Hardy, Amelia, Reuel, Anka, Meimandi, Kiana Jafari, Soder, Lisa, Griffith, Allie, Asmar, Dylan M., Koyejo, Sanmi, Bernstein, Michael S., Kochenderfer, Mykel J.
Public AI benchmark results are widely broadcast by model developers as indicators of model quality within a growing and competitive market. However, these advertised scores do not necessarily reflect the traits of interest to those who will ultimate
Externí odkaz:
http://arxiv.org/abs/2412.05520
Autor:
Piccardi, Tiziano, Saveski, Martin, Jia, Chenyan, Hancock, Jeffrey T., Tsai, Jeanne L., Bernstein, Michael
There is widespread concern about the negative impacts of social media feed ranking algorithms on political polarization. Leveraging advancements in large language models (LLMs), we develop an approach to re-rank feeds in real-time to test the effect
Externí odkaz:
http://arxiv.org/abs/2411.14652
Autor:
Park, Joon Sung, Zou, Carolyn Q., Shaw, Aaron, Hill, Benjamin Mako, Cai, Carrie, Morris, Meredith Ringel, Willer, Robb, Liang, Percy, Bernstein, Michael S.
The promise of human behavioral simulation--general-purpose computational agents that replicate human behavior across domains--could enable broad applications in policymaking and social science. We present a novel agent architecture that simulates th
Externí odkaz:
http://arxiv.org/abs/2411.10109
In spite of efforts to increase participation, many online groups struggle to survive past the initial days, as members leave and activity atrophies. We argue that a main assumption of online group design -- that groups ask nothing of their members b
Externí odkaz:
http://arxiv.org/abs/2410.23267
Autor:
Piccardi, Tiziano, Saveski, Martin, Jia, Chenyan, Hancock, Jeffrey, Tsai, Jeanne L., Bernstein, Michael S.
Social media plays a central role in shaping public opinion and behavior, yet performing experiments on these platforms and, in particular, on feed algorithms is becoming increasingly challenging. This article offers practical recommendations to rese
Externí odkaz:
http://arxiv.org/abs/2406.19571
Language models are aligned to emulate the collective voice of many, resulting in outputs that align with no one in particular. Steering LLMs away from generic output is possible through supervised finetuning or RLHF, but requires prohibitively large
Externí odkaz:
http://arxiv.org/abs/2406.00888
Data analysts have long sought to turn unstructured text data into meaningful concepts. Though common, topic modeling and clustering focus on lower-level keywords and require significant interpretative work. We introduce concept induction, a computat
Externí odkaz:
http://arxiv.org/abs/2404.12259
People rely on social skills like conflict resolution to communicate effectively and to thrive in both work and personal life. However, practice environments for social skills are typically out of reach for most people. How can we make social skill t
Externí odkaz:
http://arxiv.org/abs/2404.04204
Publikováno v:
Proc. ACM Hum.-Comput. Interact. 8, CSCW1, Article 167 (April 2024), 47 pages
Social media systems are as varied as they are pervasive. They have been almost universally adopted for a broad range of purposes including work, entertainment, activism, and decision making. As a result, they have also diversified, with many distinc
Externí odkaz:
http://arxiv.org/abs/2402.05388
The standard way to teach models is by feeding them lots of data. However, this approach often teaches models incorrect ideas because they pick up on misleading signals in the data. To prevent such misconceptions, we must necessarily provide addition
Externí odkaz:
http://arxiv.org/abs/2402.03715