SOURCE-LINKED INTELLIGENCE

Geometry of Values: Task Vector Composition for Ethical Preference Alignment in Language Models

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

Large Language Models (LLMs) are increasingly deployed in applications that must weigh clashing moral values, yet even strong models exhibit hidden biases and brittle instruction-following across languages. We introduce a 12,000-instance dataset of two-option dilemmas covering pairwise three value conflicts: Honesty vs. Justice, Justice vs. Autonomy, and Autonomy vs. Honesty, along with their translations into Hindi, Arabic, Spanish, and Chinese, to probe cross-lingual behavior. Benchmarking on GPT-5-mini reveals that it consistently favors Honesty over Autonomy across all five languages when

Read original source ↗ Open in workspace

recordType

paper

region

Global