LLMs encode functional importance over reasoning tokens, demonstrated by greedy pruning that yields shorter effective chains and attention scores that predict pruning order.
InProceedings of the 2023 Conference on Empirical Methods in Natu- ral Language Processing, pages 6342–6353, Singa- pore
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Do LLMs Encode Functional Importance of Reasoning Tokens?
LLMs encode functional importance over reasoning tokens, demonstrated by greedy pruning that yields shorter effective chains and attention scores that predict pruning order.