Search Results for author: Marcin Korecki

Found 3 papers, 0 papers with code

Biospheric AI

no code implementations31 Jan 2024 Marcin Korecki

The dominant paradigm in AI ethics and value alignment is highly anthropocentric.

Ethics

LLM Voting: Human Choices and AI Collective Decision Making

no code implementations31 Jan 2024 Joshua C. Yang, Damian Dailisan, Marcin Korecki, Carina I. Hausladen, Dirk Helbing

This paper investigates the voting behaviors of Large Language Models (LLMs), specifically GPT-4 and LLaMA-2, their biases, and how they align with human voting patterns.

Decision Making Diversity

Dynamic value alignment through preference aggregation of multiple objectives

no code implementations9 Oct 2023 Marcin Korecki, Damian Dailisan, Cesare Carissimo

The development of ethical AI systems is currently geared toward setting objective functions that align with human objectives.

Q-Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.