KCoT reframes CoT graph learning as k-means clustering by establishing a formal correspondence between Transformer blocks and k-means assignment/update steps, with a Semantic Discriminating Prompt and structure alignment yielding gains on benchmarks.
Can language models solve graph problems in natural language?Advances in Neural Information Processing Systems, 36:30840–30861, 2023a
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Clustering as Reasoning: A $k$-Means Interpretation of Chain-of-Thought Graph Learning
KCoT reframes CoT graph learning as k-means clustering by establishing a formal correspondence between Transformer blocks and k-means assignment/update steps, with a Semantic Discriminating Prompt and structure alignment yielding gains on benchmarks.