Tianhao Qian

Where an LLM stores a fact is rarely where you should erase it: high-precision storage localization picks the optimal unlearning intervention on just 17 of 36 targets, exposing a core blind spot in mechanistic model editing.

Chain-of-Thought prompting doesn't always improve LLMs' ability to solve discrete optimization problems, and surprisingly, "disordered" datasets can sometimes boost performance on simpler tasks.