Summary of Learning How to Vote with Principles: Axiomatic Insights Into the Collective Decisions Of Neural Networks, by Levin Hornischer and Zoi Terzopoulou
Learning How to Vote With Principles: Axiomatic Insights Into the Collective Decisions of Neural Networks
by Levin Hornischer, Zoi Terzopoulou
First submitted to arxiv on: 21 Oct 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel framework, axiomatic deep voting, combines neural networks with voting theory to ensure transparency in collective decision-making. The framework uses well-established axioms to evaluate and build neural networks that aggregate preferences. Key findings include: neural networks often fail to align with core voting axioms; training with axiom-specific data does not improve alignment; and solely optimizing axiom satisfaction can create new voting rules that surpass existing ones. This research offers insights for both AI and voting theory, exploring bias, value-alignment, and new areas of the space of voting rules. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Can artificial intelligence help us make better collective decisions? A team of researchers has developed a new way to use neural networks in voting theory. They want to make sure that these networks are transparent and fair when making decisions. The team found that sometimes neural networks don’t follow important rules for making collective decisions. But they also discovered that by focusing on following those rules, they can create new ways of making decisions that might be even better than what we have now. |
Keywords
» Artificial intelligence » Alignment
