research
∙
07/26/2023
Embedding Democratic Values into Social Media AIs via Societal Objective Functions
Can we design artificial intelligence (AI) systems that rank our social ...
share
research
∙
05/26/2023
Training Socially Aligned Language Models in Simulated Human Society
Social alignment in AI systems aims to ensure that these models behave a...
research
∙
01/01/2023
Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits
We present Second Thought, a new learning paradigm that enables language...
research
∙
04/18/2022
Non-Parallel Text Style Transfer with Self-Parallel Supervision
The performance of existing text style transfer models is severely limit...
research
∙
03/01/2022
Understanding Effects of Algorithmic vs. Community Label on Perceived Accuracy of Hyper-partisan Misinformation
Hyper-partisan misinformation has become a major public concern. In orde...
research
∙
08/17/2021
Modulating Language Models with Emotions
Generating context-aware language that embodies diverse emotions is an i...
research
∙
04/30/2021
Mitigating Political Bias in Language Models Through Reinforced Calibration
Current large-scale language models can be politically biased as a resul...
research
∙
01/05/2021
Political Depolarization of News Articles Using Attribute-aware Word Embeddings
Political polarization in the US is on the rise. This polarization negat...
research
∙
12/05/2020