Comment by jrmg
13 hours ago
“Westernization edits the model's weights to remove its CCP political alignment.”
That’s a very definitive statement. How?
13 hours ago
“Westernization edits the model's weights to remove its CCP political alignment.”
That’s a very definitive statement. How?
Probably some form of ablation [1] e.g. [2]. This is typically done by identifying the direction that the refusals/political alignment is represented within the model's weights and then reversing that direction.
[1] https://en.wikipedia.org/wiki/Ablation_(artificial_intellige...
[2] https://arxiv.org/abs/2603.04355 -- Efficient Refusal Ablation in LLM through Optimal Transport
It's the company's whole product offering, so I guess they probably should be definitive about it
It's following up on a dedicated report on what "westernizing" means - originally focusing on realigning geopolitical values and behavior, and now seems like it also fixes these issues in coding tasks
https://www.hirundo.io/blog/westernizing-qwen