Summary of Value Preferences Estimation and Disambiguation in Hybrid Participatory Systems, by Enrico Liscio et al.
Value Preferences Estimation and Disambiguation in Hybrid Participatory Systems
by Enrico Liscio, Luciano C. Siebert, Catholijn M. Jonker, Pradeep K. Murukannaiah
First submitted to arxiv on: 26 Feb 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL)
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 importance of understanding citizens’ values in participatory systems for effective policy-making. The authors propose a hybrid system where AI agents interact with participants to estimate their value preferences, focusing on situations where choices and motivations conflict. They operationalize the idea that valuing is deliberatively consequential, suggesting that motivations can reveal an individual’s value preferences. The authors compare methods prioritizing values estimated from motivations over choices alone, introducing a disambiguation strategy combining Natural Language Processing and Active Learning to address inconsistencies. The proposed methods are evaluated on a large-scale survey dataset on energy transition, showing improved estimation of value preferences when addressing inconsistencies. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about understanding what people want in a democracy. It’s trying to make sure that governments listen to citizens’ opinions and values. To do this, the authors created a special system where computers talk to people and try to figure out what they care most about. Sometimes, people say one thing but mean another, so the system tries to catch when this happens and ask more questions to get it right. The results show that taking these extra steps helps make sure we understand what people really want. |
Keywords
» Artificial intelligence » Active learning » Natural language processing
