Tag: Large Language Model

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

• Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement

  Published: 17 May, 2025 |  at  11:04 AM

  

  88.64 🤔

  This paper introduces Temperature Scaling (TS) and Trace Length Control for Dynamic Reasoning (TLDR) to enhance token efficiency in small language models, achieving up to 50% reduction in response length with minimal accuracy loss across multiple reasoning benchmarks.

• Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs

  Published: 17 May, 2025 |  at  11:17 PM

  

  88.54 🤔

  本文提出上下文牵引（Contextual Entrainment）现象，揭示语言模型对提示中出现token的机制性偏好，并通过可微分掩码方法识别牵引头（entrainment heads），为理解和缓解分心问题提供了新视角。

• Multiple Weaks Win Single Strong: Large Language Models Ensemble Weak Reinforcement Learning Agents into a Supreme One

  Published: 24 May, 2025 |  at  11:07 AM

  

  88.52 🤔

  本文提出LLM-Ens框架，利用大型语言模型（LLMs）通过语义状态分类和动态代理选择增强强化学习模型集成，在Atari基准上显著提升性能，最高较基线方法提升51.2%。

• Who Taught You That? Tracing Teachers in Model Distillation

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

  

  88.50 🤔

  本文提出了一种基于句法模式（PoS 模板）的方法，通过学生模型输出的高阶语言特征识别其教师模型，并在多个任务和数据集上验证了其优于传统相似度和困惑度方法的性能，但准确率仍有待提升。

• When Models Reason in Your Language: Controlling Thinking Trace Language Comes at the Cost of Accuracy

  Published: 3 Jun, 2025 |  at  11:29 AM

  

  86.23 🤔

  本文通过XReasoning基准揭示了大型推理模型在多语言推理中语言匹配与答案准确性之间的权衡，并通过提示破解和少样本后训练方法提高语言匹配率，但以牺牲准确性为代价，凸显了当前模型的局限性。