62 citations · 197 across the 9 of their papers we have counts for
Showing 2023Show all
3 papers · 1 filter
cs.HC2023★ 28 cited
Embedding Democratic Values into Social Media AIs via Societal Objective Functions
Chenyan Jia, Michelle S. Lam, Minh Chau Mai +2
Can we design artificial intelligence (AI) systems that rank our social media feeds to consider democratic values such as mitigating partisan animosity as part of their objective f…
cs.CL2023★ 17 cited
Training Socially Aligned Language Models on Simulated Social Interactions
Ruibo Liu, Ruixin Yang, Chenyan Jia +5
Social alignment in AI systems aims to ensure that these models behave according to established societal values. However, unlike humans, who derive consensus on value judgments thr…
cs.CL2023★ 12 cited
Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits
Ruibo Liu, Chenyan Jia, Ge Zhang +3
We present Second Thought, a new learning paradigm that enables language models (LMs) to re-align with human values. By modeling the chain-of-edits between value-unaligned and valu…