cs.CL（2024-08-10）

📊 共 9 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Investigating Instruction Tuning Large Language Models on Graphs	研究指令调优的大语言模型在图数据上的应用能力	large language model instruction following
2	Large Language Model-based Role-Playing for Personalized Medical Jargon Extraction	利用大语言模型角色扮演进行个性化医学术语抽取，提升患者对电子病历的理解。	large language model
3	SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning	SWIFT：一个可扩展的轻量级大模型微调基础设施	large language model foundation model
4	Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion	SpecDiff：利用扩散模型加速语言生成中的推测解码	large language model
5	Document-Level Event Extraction with Definition-Driven ICL	提出定义驱动的文档级事件抽取方法DDEE，优化LLM的prompt设计以提升事件抽取性能。	large language model
6	P3: A Policy-Driven, Pace-Adaptive, and Diversity-Promoted Framework for data pruning in LLM Training	P3：面向LLM训练的数据剪枝自适应框架，提升推理任务性能	large language model
7	Your Context Is Not an Array: Unveiling Random Access Limitations in Transformers	揭示Transformer随机访问限制：Transformer无法有效处理上下文窗口内的随机记忆访问问题	large language model
8	LaiDA: Linguistics-aware In-context Learning with Data Augmentation for Metaphor Components Identification	LaiDA：一种结合语言学知识和数据增强的隐喻成分识别方法	large language model	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
9	Path-LLM: A Shortest-Path-based LLM Learning for Unified Graph Representation	提出Path-LLM以解决统一图表示学习中的训练效率问题	representation learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页