TREC

anchor

Findings

• IC-1015GPT-J and 10 other LLMs exhibit overthinking: calibrated accuracy given incorrect few-shot demonstrations peaks at a critical layer then declines, and ablating 5 false induction heads in late layers reduces the accuracy gap by 38.9% on average [eval]
• IC-1544The latent spaces of pretrained foundational models across vision and text are not related by a single class of geometric transformations; the optimal alignment depends on the specific model pair, architecture, and dataset. [eval]
• IC-578LLMs encode input text as linearly separable representations in forerunner token hidden states, emerging in early layers and enhanced by in-context demonstrations [eval]
• IC-580The 3-step ICL inference circuit (text encoding, semantics merge, feature retrieval) is a dominant causal mechanism, as ablating the corresponding attention connections significantly degrades ICL accuracy [eval]
• IC-581Induction heads for ICL operate on task-specific attention subspaces, with partial overlap across tasks, and the geometry of these subspaces explains demonstration saturation [eval]