Tag: Large Language Model

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

• Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization

  Published: 5 Jun, 2025 |  at  11:25 AM

  

  89.45 🤔

  本文提出了一种通过迭代训练和人类反馈将提示内部化到模型权重中的方法，使基于Llama-3.1-70B的AI代理在多任务基准测试ToolQA和OfficeBench上分别达到97.9%和90.3%的成功率，超越GPT-4o和DeepSeek-V3，同时显著提升推理效率。

• CoLA: Collaborative Low-Rank Adaptation

  Published: 23 May, 2025 |  at  11:08 AM

  

  89.45 🤔

  CoLA通过提出灵活的LoRA架构和三种协作策略，结合扩展PiSSA初始化，显著提升了参数高效微调在多任务和数据稀缺场景下的性能和鲁棒性。

• RaCT: Ranking-aware Chain-of-Thought Optimization for LLMs

  Published: 1 Jun, 2025 |  at  11:51 AM

  

  89.43 🤔

  RaCT通过链式思维（CoT）提示和排序偏好优化（RPO）的两阶段训练框架，显著提升了大型语言模型在文本重排序任务中的性能，同时保留了其通用语言建模能力，在多个基准上超越基线模型。

• MELON: Provable Indirect Prompt Injection Defense via Masked Re-execution and Tool Comparison

  Published: 8 May, 2025 |  at  10:22 AM

  

  89.40 🤔

  MELON introduces a novel training-free defense against indirect prompt injection attacks on LLM agents by detecting independence of tool calls from user inputs through masked re-execution, achieving superior attack prevention (0.24% ASR on GPT-4o) and utility preservation (58.78% UA on GPT-4o) compared to existing methods.

• Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge

  Published: 24 May, 2025 |  at  11:12 AM

  

  89.35 🤔

  本文通过跨任务梯度追踪工具揭示了混合训练通过增加共享参数的数量和重要性，并在关键注意力头中集中这些参数，从而教授知识并提升语言模型的事实回忆泛化能力。