REVIEW 2 cited by
Iteration Head: A Mechanistic Study of Chain-of-Thought
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Chain-of-Thought (CoT) reasoning is known to improve Large Language Models both empirically and in terms of theoretical approximation power. However, our understanding of the inner workings and conditions of apparition of CoT capabilities remains limited. This paper helps fill this gap by demonstrating how CoT reasoning emerges in transformers in a controlled and interpretable setting. In particular, we observe the appearance of a specialized attention mechanism dedicated to iterative reasoning, which we coined "iteration heads". We track both the emergence and the precise working of these iteration heads down to the attention level, and measure the transferability of the CoT skills to which they give rise between tasks.
Forward citations
Cited by 2 Pith papers
-
Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them
GRPO produces modest math gains with small knowledge loss, while SFT gives larger math gains but degrades knowledge benchmarks more, with parameter analyses suggesting the loss comes from larger mid-layer MLP updates.
-
Large Language Models for Planning: A Comprehensive and Systematic Survey
A structured survey of LLM planning methods, benchmarks, and interpretability work, organized around a three-way taxonomy.
Discussion (0). Sign in to comment.