Taywon Min

• Taywon MinMay 25, 2025, 7:56 AM

  2 points

  0

  in reply to: ZY’s comment on: Emer­gent Misal­ign­ment: Nar­row fine­tun­ing can pro­duce broadly mis­al­igned LLMs

  But what if all insecure code contribute in some way?
  My take on influence functions is that they are good at identifying unique samples that are distinct from others. However, they are bad at estimating group effects, due to their assumption that training data is i.i.d.
  

  Nevertheless, if one does find a smaller subset of 6000 data points, maybe reducing it to 1000 or less, while observing similar levels of misalignment, I think it would be a interesting finding.

• Taywon MinFeb 24, 2025, 11:30 AM

  1 point

  0

  on: An X-Ray is Worth 15 Fea­tures: Sparse Au­toen­coders for In­ter­pretable Ra­diol­ogy Re­port Generation

  Thanks for the great work. I think that multimodal sparse auto encoders is a promising direction. Do you think it is possible /​ worthwhile to train SAEs on vla models like OpenVLA? I haven’t seen any related work training or interpreting action models using SAE work, and am curious of your thoughts.