Search Results for author:
Found 8 papers, 2 papers with code
Embedding Democratic Values into Social Media AIs via Societal Objective Functions
Finally, in Study 3, we replicate Study 1 using the democratic attitude model instead of manual labels to test its attitudinal and behavioral impact (N=558), and again find that the feed downranking using the societal objective function reduced partisan animosity (d=. 25).
Training Socially Aligned Language Models on Simulated Social Interactions
Social alignment in AI systems aims to ensure that these models behave according to established societal values.
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 models (LMs) to re-align with human values.
Non-Parallel Text Style Transfer with Self-Parallel Supervision
The performance of existing text style transfer models is severely limited by the non-parallel datasets on which the models are trained.
Modulating Language Models with Emotions
Generating context-aware language that embodies diverse emotions is an important step towards building empathetic NLP systems.
Mitigating Political Bias in Language Models Through Reinforced Calibration
Current large-scale language models can be politically biased as a result of the data they are trained on, potentially causing serious problems when they are deployed in real-world settings.
Political Depolarization of News Articles Using Attribute-aware Word Embeddings
To detect polar words, we train a multi-attribute-aware word embedding model that is aware of ideology and topics on 360k full-length media articles.
Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation
For instance, Data Boost improves F1 for the three tasks by 8. 7% on average when given only 10% of the whole data for training.
