nevenkordic/abliteration

Remove refusal behaviour from an instruct LLM by ablating the refusal direction (Arditi et al., NeurIPS 2024). Self-contained: prompt sets included; Qwen2.5-1.5B-Instruct by default.

1 best points · 0 comments · 1 Hacker News post · 1 GitHub stars · View on GitHub

Hacker News discussions

• Abliteration – Removing LLM refusal behaviors via representation engineering (1 points, 0 comments, by yotta25, 2026-10-22)