Summary of Pluralistic Alignment Over Time, by Toryn Q. Klassen et al.
Pluralistic Alignment Over Time
by Toryn Q. Klassen, Parand A. Alamdari, Sheila A. McIlraith
First submitted to arxiv on: 16 Nov 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computers and Society (cs.CY); Machine Learning (cs.LG)
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 This paper explores the challenge of evaluating an AI system’s alignment with multiple stakeholders who may have shifting preferences and values. The authors propose considering temporal aspects, such as changing satisfaction levels and temporally extended preferences, to assess the system’s pluralistic alignment over time. They draw parallels with recent work on fairness evaluation and suggest applying a similar approach to their concept of “temporal pluralism,” where the AI reflects different stakeholders’ values at distinct times. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper talks about how we can check if an artificial intelligence (AI) is making good decisions that everyone agrees with. When people have different opinions and values, it’s hard to tell if the AI is really representing what they want. The authors suggest looking at how people feel over time and their long-term goals to see if the AI is doing a good job of balancing their different views. |
Keywords
» Artificial intelligence » Alignment
