Map** social choice theory to RLHF

J Dai, E Fleisig - arxiv preprint arxiv:2404.13038, 2024 - arxiv.org
Recent work on the limitations of using reinforcement learning from human feedback (RLHF)
to incorporate human preferences into model behavior often raises social choice theory as a …

On the Existence of Envy-Free Allocations Beyond Additive Valuations

G Benadè, D Halpern, A Psomas, P Verma - arxiv preprint arxiv …, 2023 - arxiv.org
We study the problem of fairly allocating $ m $ indivisible items among $ n $ agents. Envy-
free allocations, in which each agent prefers her bundle to the bundle of every other agent …

Noise Stability of Ranked Choice Voting

S Heilman - arxiv preprint arxiv:2209.11183, 2022 - arxiv.org
We conjecture that Borda count is the ranked choice voting method that best preserves the
outcome of an election with randomly corrupted votes, among all fair voting methods with …

[PDF][PDF] Application-oriented collective decision making: experimental toolbox and dynamic environments

N Böhmer - 2023 - depositonce.tu-berlin.de
Collective decision making problems capture situations where the preferences of agents
need to be aggregated into a compromise solution. This thesis focuses on two such …

Metric distortion Under Probabilistic Voting

S Sarmasarkar, M Goyal - arxiv preprint arxiv:2405.14223, 2024 - arxiv.org
Metric distortion in social choice provides a framework for assessing how well voting rules
minimize social cost in scenarios where voters and candidates exist in a shared metric …

[PDF][PDF] Expanding our Participatory Democracy Toolkit using Algorithms, Social Choice, and Social Science

B Flanigan - 2024 - reports-archive.adm.cs.cmu.edu
In most of the world's democracies, policy decisions are primarily made by elected political
officials. However, under mounting dissatisfaction with representative government due to …