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.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
VPiT enables pretrained LLMs to perform both visual understanding and generation by predicting discrete text tokens and continuous visual tokens, with understanding data proving more effective than generation-specific data.
DoRA improves LoRA by decomposing weights into magnitude and direction and updating only direction with low-rank matrices, closing much of the gap to full fine-tuning.
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.
-
MetaMorph: Multimodal Understanding and Generation via Instruction Tuning
VPiT enables pretrained LLMs to perform both visual understanding and generation by predicting discrete text tokens and continuous visual tokens, with understanding data proving more effective than generation-specific data.
-
DoRA: Weight-Decomposed Low-Rank Adaptation
DoRA improves LoRA by decomposing weights into magnitude and direction and updating only direction with low-rank matrices, closing much of the gap to full fine-tuning.