Research map / Architectures and efficiency / Pruning and efficient tuning
DeepVoting: Learning and Improving Voting Rules with Fine-Tuning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes DeepVoting, a method that learns and improves voting rules by fine-tuning, aiming to minimize axiom violations in social choice functions.
Problem
Social choice functions cannot satisfy all desirable axioms (e.g., Arrow's Impossibility Theorem), and prior work learns rules that minimize axiom violations; the abstract is truncated so the specific gap is only partly visible.
Approach
Uses fine-tuning to learn and improve voting rules so as to reduce axiom violations; the abstract states only this general direction, so the specific mechanism is not confirmed.
Experimental setup
Builds on: DeepVoting prior work on learned voting rules
Closest papers by meaning
- Explainable Voting (NeurIPS 2020 · similarity 0.89)
- What Voting Rules Actually Do: A Data-Driven Analysis of Multi-Winner Voting (AAAI 2026 · similarity 0.89)
- Learning to Elect (NeurIPS 2021 · similarity 0.88)
- Proportional Aggregation of Preferences for Sequential Decision Making (AAAI 2024 · similarity 0.85)
- Learning to Manipulate Under Limited Information (AAAI 2025 · similarity 0.85)
- Computing Voting Rules with Improvement Feedback (ICML 2025 · similarity 0.85)
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.