Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Values
The rapid integration of Large Language Models (LLMs) in high-stakes decision-making -- such as allocating scarce resources like donor organs -- raises critical questions about their alignment with human moral values. We systematically evaluate the behavior of several prominent LLMs against human preferences in kidney allocation scenarios and show that LLMs: i) exhibit stark deviations from human values in prioritizing various attributes, and ii) in contrast to humans, LLMs rarely express indecision, opting for deterministic decisions even when alternative indecision mechanisms (e.g., coin flipping) are provided. Nonetheless, we show that low-rank supervised fine-tuning with few samples is often effective in improving both decision consistency and calibrating indecision modeling. These findings illustrate the necessity of explicit alignment strategies for LLMs in moral/ethical domains.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingSimilar Papers 제목 키워드 기반
Moral Change or Noise? On Problems of Aligning AI With Temporally Unstable Human Feedback
Alignment methods in moral domains seek to elicit moral preferences of human stakeholders and incorporate them into AI. This presupposes moral preferences as static targets, but such preferences often evolve over time. P…
Indecision Modeling
AI systems are often used to make or contribute to important decisions in a growing range of applications, including criminal justice, hiring, and medicine. Since these decisions impact human lives, it is important that …
PhilosophyCan AI Model the Complexities of Human Moral Decision-Making? A Qualitative Study of Kidney Allocation Decisions
A growing body of work in Ethical AI attempts to capture human moral judgments through simple computational models. The key question we address in this work is whether such simple AI models capture {the critical} nuances…
Decision MakingAligning with Heterogeneous Preferences for Kidney Exchange
AI algorithms increasingly make decisions that impact entire groups of humans. Since humans tend to hold varying and even conflicting preferences, AI algorithms responsible for making decisions on behalf of such groups e…
Decision MakingFoundational Moral Values for AI Alignment
Solving the AI alignment problem requires having clear, defensible values towards which AI systems can align. Currently, targets for alignment remain underspecified and do not seem to be built from a philosophically robu…
Philosophy