Reproduce “From Opinions to Commitments: Unstable Assignments and Silent Choices in AI-Mediated Proposals” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Sachit Mahajan, Javier Argota S{á}nchez-Vaquerizo, Arthur Capozzi, Dirk Helbing
The authors test whether AI mediators keep proposed policy assignments stable when opinion order changes and whether prompt objectives affect whose views appear. On DeliberationBank, mixed assignment sets occurred in 16.7% of order reruns versus 20.3% with new opinion samples. Agreement prompts favored higher-support views in coverage judgments, but proposals were not validated as endorsed or justified.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.