Saved in:
Bibliographic Details
Main Authors: Agnihotri, Shashank, Jakubassa, Jonas, Dey, Priyam, Goyal, Sachin, Schiele, Bernt, Radhakrishnan, Venkatesh Babu, Keuper, Margret
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.02768
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908574403264512
author Agnihotri, Shashank
Jakubassa, Jonas
Dey, Priyam
Goyal, Sachin
Schiele, Bernt
Radhakrishnan, Venkatesh Babu
Keuper, Margret
author_facet Agnihotri, Shashank
Jakubassa, Jonas
Dey, Priyam
Goyal, Sachin
Schiele, Bernt
Radhakrishnan, Venkatesh Babu
Keuper, Margret
contents Open-weight LLMs can be modified at inference time with simple activation edits, which raises a practical question for safety: do common safety interventions like refusal training or metatag training survive such edits? We study model abliteration, a lightweight projection technique designed to remove refusal-sensitive directions, and conduct a controlled evaluation across a granular sequence of Safety Pretraining checkpoints for SmolLM2-1.7B, alongside widely used open baselines. For each of 20 systems, original and abliterated, we issue 100 prompts with balanced harmful and harmless cases, classify responses as **Refusal** or **Non-Refusal** using multiple judges, and validate judge fidelity on a small human-labeled subset. We also probe whether models can identify refusal in their own outputs. Our study produces a checkpoint-level characterization of which data-centric safety components remain robust under abliteration, quantifies how judge selection influences evaluation outcomes, and outlines a practical protocol for integrating inference-time edits into safety assessments. Code: https://github.com/shashankskagnihotri/safety_pretraining.
format Preprint
id arxiv_https___arxiv_org_abs_2510_02768
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Granular Study of Safety Pretraining under Model Abliteration
Agnihotri, Shashank
Jakubassa, Jonas
Dey, Priyam
Goyal, Sachin
Schiele, Bernt
Radhakrishnan, Venkatesh Babu
Keuper, Margret
Machine Learning
Computation and Language
Open-weight LLMs can be modified at inference time with simple activation edits, which raises a practical question for safety: do common safety interventions like refusal training or metatag training survive such edits? We study model abliteration, a lightweight projection technique designed to remove refusal-sensitive directions, and conduct a controlled evaluation across a granular sequence of Safety Pretraining checkpoints for SmolLM2-1.7B, alongside widely used open baselines. For each of 20 systems, original and abliterated, we issue 100 prompts with balanced harmful and harmless cases, classify responses as **Refusal** or **Non-Refusal** using multiple judges, and validate judge fidelity on a small human-labeled subset. We also probe whether models can identify refusal in their own outputs. Our study produces a checkpoint-level characterization of which data-centric safety components remain robust under abliteration, quantifies how judge selection influences evaluation outcomes, and outlines a practical protocol for integrating inference-time edits into safety assessments. Code: https://github.com/shashankskagnihotri/safety_pretraining.
title A Granular Study of Safety Pretraining under Model Abliteration
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2510.02768