Geometry of Values: Task Vector Composition for Ethical Preference Alignment in Language Models
Researchers build a 12,000-dilemma multilingual dataset and use orthogonalized task vectors to isolate and steer ethical value preferences in LLMs.
The paper introduces a 12,000-instance dataset of two-option moral dilemmas spanning Honesty vs. Justice, Justice vs. Autonomy, and Autonomy vs. Honesty conflicts, translated into Hindi, Arabic, Spanish, and Chinese. GPT-5-mini consistently favored Honesty over Autonomy across all five languages, while Llama-3.2-1/3B showed strong first-option bias that plain fine-tuning and DPO removed, lifting accuracy above 98%. Orthogonalizing value preference task vectors against the general instruction-following vector enabled task arithmetic to produce a model with the opposite value stance.
- 12,000-instance dilemma dataset covers three value conflicts in five languages
- GPT-5-mini consistently prefers Honesty over Autonomy when no policy is given
- DPO and fine-tuning remove Llama-3.2 first-option bias, exceeding 98% accuracy
- Orthogonalized task vectors enable steering a model to opposite value stances
From the original article
1 min read at huggingface.co
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.
By Utkarsh Agarwal, Monojit Choudhury · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.