Cliff tokens are single tokens triggering LLM math reasoning failures, identified via adaptive z-test threshold on token potential; a taxonomy and Cliff-DPO optimization yield up to +6.6 accuracy gains.
Hasan Abed Al Kader Hammoud, Hani Itani, and Bernard Ghanem
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Prefix consistency weights CoT answers by their regeneration frequency from truncated prefixes and reaches standard self-consistency accuracy at a median 4.6x fewer tokens across five models and four benchmarks.
ATTNPO guides process-supervised RL with intrinsic attention signals to shorten reasoning traces while raising accuracy on nine benchmarks.
citing papers explorer
-
Cliff Tokens: Identifying Single-Token Failure Triggers in LLM Mathematical Reasoning
Cliff tokens are single tokens triggering LLM math reasoning failures, identified via adaptive z-test threshold on token potential; a taxonomy and Cliff-DPO optimization yield up to +6.6 accuracy gains.
-
Reliable Chain-of-Thought via Prefix Consistency
Prefix consistency weights CoT answers by their regeneration frequency from truncated prefixes and reaches standard self-consistency accuracy at a median 4.6x fewer tokens across five models and four benchmarks.
-
ATTNPO: Attention-Guided Process Supervision for Efficient Reasoning
ATTNPO guides process-supervised RL with intrinsic attention signals to shorten reasoning traces while raising accuracy on nine benchmarks.