Saved in:
Bibliographic Details
Main Author: Pollanen, Marco
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.17260
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908785509924864
author Pollanen, Marco
author_facet Pollanen, Marco
contents Direct Preference Optimization (DPO) is often tuned as if increasing alignment pressure (controlled by $β$) yields progressively "better" behavior. We instead treat $β$ as a control parameter and densely sweep it for three 7B open-weight families under a fixed DPO recipe. In Mistral, capability is sharply non-monotonic: aggregated logic-probe margins become positive only in a narrow band near $β\approx 10^{-2}$ and revert outside it, with boundary points that are seed-sensitive. Across architectures under the same sweep, we observe qualitatively different response modes: sharp reorganization in Mistral, selective changes in Llama, and smooth trade-offs in Qwen. Critically, the DPO preference margin can anticorrelate with reasoning capability (Pearson $r=-0.91$ for Llama logic), so margin-based selection can prefer capability-impaired models. Training path also matters: exposure to high $β$ induces capability losses that persist even after $β$ is reduced (hysteresis). These findings motivate capability-resolved evaluation across the $β$ landscape rather than reliance on margins or aggregate benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17260
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle The Viscosity of Logic: Phase Transitions and Hysteresis in DPO Alignment
Pollanen, Marco
Machine Learning
Artificial Intelligence
Direct Preference Optimization (DPO) is often tuned as if increasing alignment pressure (controlled by $β$) yields progressively "better" behavior. We instead treat $β$ as a control parameter and densely sweep it for three 7B open-weight families under a fixed DPO recipe. In Mistral, capability is sharply non-monotonic: aggregated logic-probe margins become positive only in a narrow band near $β\approx 10^{-2}$ and revert outside it, with boundary points that are seed-sensitive. Across architectures under the same sweep, we observe qualitatively different response modes: sharp reorganization in Mistral, selective changes in Llama, and smooth trade-offs in Qwen. Critically, the DPO preference margin can anticorrelate with reasoning capability (Pearson $r=-0.91$ for Llama logic), so margin-based selection can prefer capability-impaired models. Training path also matters: exposure to high $β$ induces capability losses that persist even after $β$ is reduced (hysteresis). These findings motivate capability-resolved evaluation across the $β$ landscape rather than reliance on margins or aggregate benchmarks.
title The Viscosity of Logic: Phase Transitions and Hysteresis in DPO Alignment
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2601.17260