← Explore Research Questions

Resource

Elicitation Inference Optimization for Multi-Principal-Agent Alignment

Research on elicitation inference methods for aggregating and understanding collective preferences from participant inputs.

Research

Link https://openreview.net/pdf?id=tkxnRPkb_H

Creators Andrew Konya, Aviv Ovadya, Yeping Lina Qiu and Michael P Varga

Year 2022

Related Capabilities

Aggregate perspectives

Representativeness

Ability to aggregate votes and distill more complex forms of open-ended input into outputs and decisions, in fair and understandable ways, such that participants feel their contributions are meaningfully taken into account (and can ideally see how).

Related Research Questions

How can we best embed traceability and transparency into the aggregation/distillation process?

Relevant disciplines

Ethics & Philosophy Public Policy & Law

What are the best standardized models for 'in-person' (in real world or online) facilitators to follow as they collate and record views of participants?

Relevant disciplines

Communication & Media Education & Learning

What are the best methods for generating and integrating effective, actionable and value-aligned proposals for bridging divides?

Relevant disciplines

Political Science Conflict & Peace Studies

When should we route divergent info to help participants understand the full range of perspectives, and when should we route convergent info to help find consensus?

Relevant disciplines

Psychology Education & Learning