Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.
Adaptivestep: Automatically dividing reasoning step through model confidence
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
PDCR improves vision-language reasoning by computing separate normalized confidence advantages for perception steps and reasoning steps after unsupervised decomposition.
DGPO is a critic-free RL framework that uses bounded Hellinger distance and entropy-gated advantage redistribution to enable fine-grained token-level credit assignment in long CoT generations for LLM alignment, reporting SOTA results on AIME benchmarks.
A survey organizing techniques to achieve efficient reasoning in LLMs by shortening chain-of-thought outputs.
The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.
citing papers explorer
-
Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost
Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.
-
PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning
PDCR improves vision-language reasoning by computing separate normalized confidence advantages for perception steps and reasoning steps after unsupervised decomposition.
-
DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignment
DGPO is a critic-free RL framework that uses bounded Hellinger distance and entropy-gated advantage redistribution to enable fine-grained token-level credit assignment in long CoT generations for LLM alignment, reporting SOTA results on AIME benchmarks.
-
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
A survey organizing techniques to achieve efficient reasoning in LLMs by shortening chain-of-thought outputs.
-
From System 1 to System 2: A Survey of Reasoning Large Language Models
The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.