# Study Finds Standard Post-Training Can Erode Values Instilled During Pretraining

Optimizing models to be helpful through supervised fine-tuning and reinforcement learning degraded compassion-related behaviors in some domains, the paper reports.

- Published: 2026-06-26T10:45:35.415Z
- Canonical: https://polylog.news/ai/2026-06-26/study-finds-standard-post-training-can-erode-values-instille
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv cs.CL (Helpfulness Hurts)](https://arxiv.org/abs/2606.26102)

A new paper, Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training, examines a side effect of the standard alignment pipeline. Supervised fine-tuning and reinforcement learning are applied to m…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-06-26/study-finds-standard-post-training-can-erode-values-instille (subscription information: https://polylog.news/pricing).