Human realignment
TL;DR
It is found that at least for the time being, explicit normative instructions are not fully able to realign AI advice with the normative convictions of the population, or the legislator deciding on its behalf.
Abstract
Recent advances in AI make it conceivable to delegate legal decision-making to machines, or to enhance human adjudication through AI assistance. Using classic normative conflicts — the trolley problem and comparable moral dilemmas — as a proof of concept, we examine the alignment between AI legal reasoning and human judgment. In our baseline experiment, we find a pronounced mismatch between decisions made by GPT and those of human subjects. This misalignment raises substantive concerns for AI-powered legal decision-aids. We investigate whether explicit normative guidance can address this misalignment, with mixed results. is susceptible to such intervention, but frequently refuses to decide when faced with a moral dilemma. is outright utilitarian, and essentially ignores the instruction to decide on deontological grounds. faithfully implements this instruction, but is unwilling to balance deontological and utilitarian concerns if instructed to do so. We replicate the experiment with four LLMs from different providers. comes closest to human respondents. is most sensitive to normative instructions. and have a strong utilitarian bias, and do not strongly respond to normative interventions. At least for the time being, explicit normative instructions are not fully able to realign AI advice with the normative convictions of the population, or the legislator deciding on its behalf.