遇见数据集

Quantization Does Not Undo Abliteration: A Measurement Study of Refusal in Compressed Language Models (artifact)

收藏
Zenodo2026-10-27 更新2026-10-29 收录
官方服务:

资源简介:

Artifact for the ARTMAN 2026 (ACSAC workshop) paper. Evaluation prompts, judge verdicts for all 46,600 generations (response text replaced by SHA-256), human annotation labels, checkpoint-differencing and rank-sweep measurements, and the code that produces every table and figure in the paper. Raw model responses are distributed as a separate restricted file on this record.

提供机构:
Zenodo
创建时间:
2026-10-27
二维码
社区交流群
二维码
科研交流群
商业服务