cs.CL（2024-08-13）

📊 共 18 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (15 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Amuro and Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models	研究预训练与微调关系：持续预训练提升模型潜在能力，微调后模型对prompt更敏感。	large language model
2	A Perspective on Large Language Models, Intelligent Machines, and Knowledge Acquisition	探讨大语言模型在知识获取和理解抽象概念方面的局限性	large language model
3	A semantic embedding space based on large language models for modelling human beliefs	利用大型语言模型构建语义嵌入空间，建模人类信念体系	large language model
4	Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas	通过模拟合成角色评估大型语言模型的文化适应性	large language model
5	LoRA$^2$ : Multi-Scale Low-Rank Approximations for Fine-Tuning Large Language Models	提出LoRA$^2$以提高大语言模型微调的参数效率	large language model
6	SparkRA: A Retrieval-Augmented Knowledge Service System Based on Spark Large Language Model	SparkRA：基于星火大语言模型的检索增强知识服务系统，提供科研辅助功能。	large language model
7	Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives	Re-TASK框架通过能力、技能和知识视角，提升LLM在特定领域任务中的表现。	large language model chain-of-thought	✅
8	Leveraging Language Models for Emotion and Behavior Analysis in Education	利用大语言模型和提示工程进行教育领域的情绪和行为分析	large language model chain-of-thought
9	IFShip: Interpretable Fine-grained Ship Classification with Domain Knowledge-Enhanced Vision-Language Models	提出IFShip以解决遥感细粒度船舶分类的可解释性问题	instruction following chain-of-thought	✅
10	Social Debiasing for Fair Multi-modal LLMs	提出CMSC数据集与CSD策略，解决多模态大语言模型中的社会偏见问题	large language model
11	AquilaMoE: Efficient Training for MoE Models with Scale-Up and Scale-Out Strategies	AquilaMoE：通过Scale-Up和Scale-Out策略高效训练MoE模型	large language model
12	ELLA: Empowering LLMs for Interpretable, Accurate and Informative Legal Advice	ELLA：增强LLM在法律咨询中的可解释性、准确性和信息量	large language model
13	Layerwise Recurrent Router for Mixture-of-Experts	提出层间循环路由RMoE，提升混合专家模型参数效率	large language model	✅
14	Bridging LLMs and KGs without Fine-Tuning: Intermediate Probing Meets Subgraph-Aware Entity Descriptions	提出基于中间层探查和子图感知实体描述的框架，无需微调即可桥接LLM与KG，实现高效知识图谱补全。	large language model
15	Pragmatic inference of scalar implicature by LLMs	研究LLM对标量蕴涵的语用推理能力，揭示BERT和GPT-2的不同机制	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	🔗	⭐
16	Can Advanced LLMs Coach Smaller LLMs? Knowledge Distillation for Goal-Oriented Dialogs	提出GER框架，通过知识蒸馏提升小模型在目标导向对话中的性能。	distillation
17	LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs	LongWriter：通过长输出数据对齐，解锁长上下文LLM的万字以上生成能力	DPO large language model	✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
18	Fingerspelling within Sign Language Translation	提出基于字符级tokenization的手语翻译模型，提升对手指语的理解能力	open-vocabulary open vocabulary

⬅️ 返回 cs.CL 首页 · 🏠 返回主页