Check Your LLM's Secret Dictionary! Five Lines of Code Reveal What Your LLM Learned (Including What It Shouldn't Have) 事件

Check Your LLM's Secret Dictionary! Five Lines of Code Reveal What Your LLM Learned (Including What It Shouldn't Have) arXiv:2605.22005v1 Announce Type: cross Abstract: We show that singular value decomposition of the lm_head} weight matrix of a transformer-based large language model -- requiring only five lines of PyTorch and no model inference -- reveals interpretable semantic subspaces directly from the model weights. Each left singular vector identifies the vocabulary tokens most readily se