cs.CVNov 18, 2026

Can Weight-Space Programming Alter Learned Ethical Priorities?

Authors: Kai Yi Ji

Abstract

We investigate whether a weight edit can alter how a model trades off honoring a commitment against benefiting more people. In a concept-supervised text model, we alter fitted choice weights so that the benefit required to override a formal pledge is larger than for an ordinary promise. Across six independently trained text readers, the edit selects the larger group in both orders on 100% of targeted ordinary conflicts and 83.3% of targeted formal conflicts. It preserves the source model's success rates on smaller conflicts and its factual accuracy. The remaining formal-conflict failures coincide with errors reading a beneficiary number. A separate classifier demonstrates why this distinction matters: reusing a factual answer passes an unconditional choice test but fails to preserve small-gap promises. In a YOLO11n pilot on COCO128, a bias edit increased small-target matches from 3/43 to 9/43, and an equivalent score calibration reproduced the retained detections. These exploratory results show a way to test selective changes to learned priorities in a model with an exposed trade-off mechanism. Whether the method can discover such changes in less structured language models remains open.

Figures & tables

Explore similar work

CardsList
  1. Weight-Space Programming Changes How an LLM Uses Python for Computational Biology

    Nov 16, 2026Makoto SatoLanguage Model EditingLLM Tool Use

  2. Resisting Harmful Instructions through Training-Free Weight Editing

    Oct 15, 2026Ali Ebrahimpour-Boroojeny, Xiaocong Yang, Samuel Schapiro +4LLM SafetyLLM Safety Alignment

  3. Weight Space Programming for Vision Language Model Repair

    Nov 17, 2026Avinash Goutham Aluguvellyweight-space programmingFault Localization