Research map / Large language models / AI and society
A Voting-Based System for Ethical Decision Making
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Increase pairwise comparisons per voter from 30 to 100 | TM preference learning · Synthetic data, N=20 | accuracy: 84.3% -> 92.4% | Helped |
| Summarize voter models by averaging their parameters | TM aggregation · Synthetic data, Step III | accuracy: 93.9% | Helped |
| Use a single mean-parameter TM model instead of the mean voter profile | Ethical decision system · Moral Machine | accuracy: 98.2% at 2 alternatives; 95.1% at 10 | Mixed |
| Increase the number of pairwise comparisons per voter | TM preference learning · Synthetic data, N=40 | accuracy: 89.3% -> 94.9% | Helped |
| Use 3 alternatives per instance | TM preference learning · Synthetic data, Step II | accuracy: 88.8% with 30 comparisons; 93.5% with 100 comparisons | Mixed |
| Use 3 alternatives per instance | Mean-parameter TM summary · Synthetic data, Step III | accuracy: 96.2% | Helped |
| Increase feature dimension to d=20 | TM preference learning · Synthetic data, Step II | accuracy: 74.6% with 30 comparisons; 88.2% with 100 comparisons | Hurt |
| Increase feature dimension to d=20 | Mean-parameter TM summary · Synthetic data, Step III | accuracy: 94.7% | Helped |
Closest papers by meaning
- SCRUPLES: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotes (AAAI 2021 · similarity 0.88)
- Towards a More Burkean Approach to Computational Social Choice (AAAI 2024 · similarity 0.84)
- Position: Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback (ICML 2024 · similarity 0.84)
- Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties (AAAI 2024 · similarity 0.83)
- MoralReason: Generalizable Moral Decision Alignment for LLM Agents Using Reasoning-Level Reinforcement Learning (AAAI 2026 · similarity 0.82)
- Proportional Aggregation of Preferences for Sequential Decision Making (AAAI 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.