Human realignment

Christoph Engel

doi:10.1007/s10506-026-09517-6

Return

Human realignment

2026-08-17

Christoph Engel *

Yoan Hermstrüwer

Alison Kim

DOI：10.1007/s10506-026-09517-6

Original

Save

View PDF

Abstract

En 中文

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. GPT-3.5 is susceptible to such intervention, but frequently refuses to decide when faced with a moral dilemma. GPT-4 is outright utilitarian, and essentially ignores the instruction to decide on deontological grounds. GPT-o3-mini 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. Claude-sonnet-4.6 comes closest to human respondents. Gemini-2.5-flash-lite is most sensitive to normative instructions. Llama-4-scout and Mistral-nemo 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.

Keywords:

Large language models

Human-AI alignment

Rule of law

Moral dilemmas

Trolley problems