Language Models are Unsupervised Multitask Learners

Similar preprints — Semantic Scholar

Cited by (3)

• Evaluating Language Model Character Traits

  Claude-instant-1.2 achieves 91.1% accuracy and 88.6% logical coherence on 696 valid Leap-of-Thought entailment tuples — highest among 15 tested models including GPT-4 (89.9% accuracy, 84.7% coherence)

• The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?

  Under arbitrarily powerful alignment maps, causal abstraction becomes vacuous: any neural network can be perfectly mapped to any algorithm, a result proven formally in Theorem 1 under five mild assump

• The Platonic Representation Hypothesis

  Neural networks trained on different data modalities, architectures, and objectives are converging toward a shared statistical model of reality — what the paper terms the "platonic representation" — f