Summary of Mapping Social Choice Theory to Rlhf, by Jessica Dai et al.
Mapping Social Choice Theory to RLHF
by Jessica Dai, Eve Fleisig
First submitted to arxiv on: 19 Apr 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computers and Society (cs.CY)
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 study bridges the gap between reinforcement learning from human feedback (RLHF) and social choice theory to better incorporate human preferences into model behavior. The research analyzes key differences between problem settings in social choice and RLHF, shedding light on how these distinctions impact the interpretation of well-known technical results in social choice. By combining insights from both fields, this study aims to provide a more comprehensive understanding of how to aggregate human preferences amid disagreement. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study takes two existing ideas and brings them together. Social choice theory helps us understand how people make decisions when they don’t all agree. RLHF is a way for computers to learn from humans by getting feedback on what’s good or bad. The researchers looked at the similarities and differences between these two areas and talked about how this comparison can help us better use human preferences in computer models. |
Keywords
» Artificial intelligence » Reinforcement learning from human feedback » Rlhf
