k-nearest neighbours classifier / Nearest-neighbor baseline

anchor

Classifies a point by the labels of its closest neighbours. As a probe it tests whether a property is recoverable from local neighbourhood structure, which is a weaker requirement than linear separability.

Findings

• IC-028SPADE, an abstaining classifier built on top of ResNet, ViT, and VGG models, detects out-of-distribution and adversarial samples with provable guarantees. [compared-to]
• IC-1003Pretrained ResNet-50 and ViT-B/16 exhibit neuron activation patterns that are separable between in-distribution and out-of-distribution inputs, enabling post-hoc OOD detection without model modification [compared-to]
• IC-1220GPT-4, GPT-3.5-turbo, and Llama-2-70B can implement learning algorithms in-context on novel boolean functions, competing with nearest-neighbor baselines [compared-to]
• IC-1221LLM performance on in-context boolean function learning is scale-dependent, with GPT-2 failing and Llama-2 models improving gradually with size [compared-to]
• TM-008TerraMind embeddings separate hemispheres rather than climate zones [primary]