Published November 16, 2026
| Version v1.1
Dataset
Open
Quantization Does Not Undo Abliteration / Substring Refusal Detection Fabricates Safety Effects under Quantization (artifact)
Authors/Creators
- 1. University of Nevada, Las Vegas
- 2. West Career and Technical Academy
Description
Artifact for two ACSAC 2026 workshop papers (ARTMAN 2026 and CSET 2026). Evaluation prompts, judge verdicts for all 46,600 generations (response text replaced by SHA-256), human annotation labels (132 reference labels plus 300 second-annotator labels), checkpoint-differencing and rank-sweep measurements, the judge ablation, the failure-mode decomposition, the language-switch mechanism experiments, and the code that produces every table and figure in both papers. Raw model responses are distributed through a separate restricted record.
Files
yxk14/quant-abliteration-v1.1.zip
Additional details
Related works
- Is supplement to
- https://github.com/yxk14/quant-abliteration (URL)
- Is supplemented by
- 10.5281/zenodo.23680595 (DOI)
Software
- Repository URL
- https://github.com/yxk14/quant-abliteration