#recall News & Analysis

Disentangling Recall and Reasoning in Transformer Models through Layer-wise Attention and Activation Analysis

Researchers used mechanistic interpretability techniques to demonstrate that transformer language models have distinct but interacting neural circuits for recall (retrieving memorized facts) and reasoning (multi-step inference). Through controlled experiments on Qwen and LLaMA models, they showed that disabling specific circuits can selectively impair one ability while leaving the other intact.