cs.CL（2024-09-08）

📊 共 7 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签	🔗
1	Seemingly Plausible Distractors in Multi-Hop Reasoning: Are Large Language Models Attentive Readers?	揭示大型语言模型在多跳推理中易受看似合理的干扰信息影响	large language model
2	MHS-STMA: Multimodal Hate Speech Detection via Scalable Transformer-Based Multilevel Attention Framework	提出基于Transformer的多层注意力框架MHS-STMA，用于可扩展的多模态仇恨言论检测。	multimodal
3	Evaluating Large Language Models with Tests of Spanish as a Foreign Language: Pass or Fail?	利用西班牙语能力测试评估大型语言模型：通过还是失败？	large language model
4	Socially Responsible Data for Large Multilingual Language Models	为多语言大模型构建社会责任数据：关注伦理与公平	large language model
5	OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs	OneGen：提出一种高效的单次前向统一生成与检索框架，提升LLM在复合任务上的性能。	large language model
6	WaterSeeker: Pioneering Efficient Detection of Watermarked Segments in Large Documents	WaterSeeker：高效检测大型文档中水印文本片段，提升AI生成内容溯源能力	large language model	✅
7	InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference	InstInfer：面向长文本LLM推理，提出基于计算存储的Attention卸载方案，提升成本效益。	large language model