cs.CL（2024-05-19）

📊 共 11 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) (9 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Exploring the Capabilities of Prompted Large Language Models in Educational and Assessment Applications	探索提示工程驱动的大语言模型在教育与评估领域的应用潜力	large language model chain-of-thought
2	MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models	MeteoRA：面向大语言模型的多任务嵌入式LoRA框架，实现高效自主的任务切换。	large language model
3	A Multi-Perspective Analysis of Memorization in Large Language Models	多视角分析大型语言模型中的记忆现象，揭示模型规模、上下文长度等因素的影响。	large language model
4	SemEval-2024 Task 3: Multimodal Emotion Cause Analysis in Conversations	SemEval-2024 Task 3旨在通过多模态情感因果分析，提升对话场景下类人AI的情感理解能力。	multimodal
5	EmbSum: Leveraging the Summarization Capabilities of Large Language Models for Content-Based Recommendations	EmbSum：利用大语言模型的摘要能力进行内容推荐，提升用户个性化体验。	large language model
6	MAML-en-LLM: Model Agnostic Meta-Training of LLMs for Improved In-Context Learning	提出MAML-en-LLM，通过模型无关的元学习提升LLM的上下文学习能力。	large language model
7	Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts	提出DeCK方法，通过对比知识解码增强LLM对编辑事实的置信度	large language model
8	Effective In-Context Example Selection through Data Compression	提出基于数据压缩的上下文示例选择方法，提升大语言模型性能	large language model
9	MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation	提出MHPP数据集，用于更全面评估语言模型在复杂Python代码生成中的能力。	large language model	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
10	Large Language Models are Biased Reinforcement Learners	大型语言模型在强化学习中表现出相对价值偏差	reinforcement learning large language model
11	Simple-Sampling and Hard-Mixup with Prototypes to Rebalance Contrastive Learning for Text Classification	提出SharpReCL模型，通过原型采样和Hard-Mixup重平衡对比学习，解决文本分类中的数据不平衡问题。	contrastive learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页