Tag: Large Language Model

All the articles with the tag "Large Language Model".

• LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Merging

  Published: 28 May, 2025 |  at  11:22 AM

  

  91.54 🤔

  本文提出LORE-MERGING框架，通过低秩估计构建近似基础模型和任务向量，无需访问原始基础模型即可实现模型合并，并在多个基准数据集上展现出优于传统方法的性能。

• Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Models

  Published: 8 May, 2025 |  at  06:12 PM

  

  91.54 🤔

  This paper introduces Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning (LS-Mixture SFT), which combines long and short CoT datasets to fine-tune non-reasoning LLMs, achieving a 2.3% average accuracy improvement and 47.61% response length reduction on reasoning benchmarks.

• ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training

  Published: 22 May, 2025 |  at  11:23 AM

  

  91.42 🤔

  ZeroTuning提出了一种无需训练的方法，通过调整大型语言模型初始token的注意力分布，在文本分类、问答和多轮对话任务中显著提升性能，同时展现出对资源限制和长上下文的鲁棒性。

• Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning

  Published: 24 May, 2025 |  at  11:13 AM

  

  91.13 🤔

  本文提出Long⊗Short框架，通过长思维和短思维LLM协作推理，利用自动思维分块、冷启动SFT和多轮RL优化，显著提升推理效率，在多个基准上使Qwen2.5-7B和Llama3.1-8B性能接近蒸馏模型，同时减少token长度超80%。

• Training Language Models to Reason Efficiently

  Published: 24 May, 2025 |  at  11:14 AM

  

  91.10 🤔

  本文提出了一种通过强化学习训练大型推理模型以高效推理的方法，利用长度惩罚目标函数和可调参数α显著降低推理成本，同时在多个数学数据集上保持大部分准确性。