Tag: Large Language Model

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

• Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs

  Published: 8 May, 2025 |  at  11:07 AM

  

  94.57 🤔

  This paper proposes a three-dimensional taxonomy and develops TTP and HarmFormer tools to filter harmful content from web-scale LLM pretraining datasets, revealing significant toxicity prevalence and persistent safety gaps through benchmarks like HAVOC.

• 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.

• CoordField: Coordination Field for Agentic UAV Task Allocation In Low-altitude Urban Scenarios

  Published: 8 May, 2025 |  at  12:16 AM

  

  90.99 🤔

  本文提出了一种基于协调场的代理系统（CoordField），通过大型语言模型解析自然语言指令并利用动态势场实现异构无人机群在城市环境中的去中心化任务分配，实验验证了其在任务覆盖、响应时间和动态适应性方面的优越性能。

• Agentic AI: The Era of Semantic Decoding

  Published: 8 May, 2025 |  at  12:27 AM

  

  89.68 🤔

  本文提出语义解码视角，将大型语言模型、人类和工具的协作框架化为语义空间中的优化过程，通过语义令牌的交换和语义解码算法的设计探索AI系统的新计算范式。

• 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.