cs.CL（2024-05-10）

📊 共 20 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Improving Instruction Following in Language Models through Proxy-Based Uncertainty Estimation	提出基于代理的语言模型不确定性评估方法，提升指令遵循能力。	instruction following
2	LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play	提出LLM Discussion框架，通过讨论和角色扮演提升大语言模型的创造力	large language model	✅
3	SaudiBERT: A Large Language Model Pretrained on Saudi Dialect Corpora	提出SaudiBERT，一个基于沙特方言语料预训练的大型语言模型，显著提升沙特方言文本理解任务性能。	large language model	✅
4	A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models	综述检索增强大语言模型（RA-LLMs）：利用外部知识提升生成质量	large language model	✅
5	Mitigating Hallucinations in Large Language Models via Self-Refinement-Enhanced Knowledge Retrieval	提出Re-KGR，通过自精炼知识检索缓解大语言模型中的幻觉问题	large language model
6	Prompting Large Language Models with Knowledge Graphs for Question Answering Involving Long-tail Facts	提出LTGen基准，研究知识图谱增强大语言模型在长尾知识问答中的有效性	large language model
7	LyS at SemEval-2024 Task 3: An Early Prototype for End-to-End Multimodal Emotion Linking as Graph-Based Parsing	LyS提出基于图解析的多模态情感链接端到端原型系统，用于对话情感原因分析。	multimodal
8	Can Large Language Models Replicate ITS Feedback on Open-Ended Math Questions?	利用大语言模型复现智能辅导系统对开放式数学题的反馈	large language model
9	Execution-Based Evaluation of Natural Language to Bash and PowerShell for Incident Remediation	提出基于执行的评估平台，用于评估LLM生成的Bash和PowerShell脚本在事件修复中的有效性。	large language model
10	LLM-Generated Black-box Explanations Can Be Adversarially Helpful	揭示LLM黑盒解释的对抗性帮助风险，可能误导人类和LLM评估器	large language model
11	What Can Natural Language Processing Do for Peer Review?	探讨自然语言处理在同行评审中的应用，为机器辅助评审提供基础。	large language model
12	Potential and Limitations of LLMs in Capturing Structured Semantics: A Case Study on SRL	提出PromptSRL，评估大型语言模型在语义角色标注任务中捕获结构化语义的能力。	large language model
13	Pruning as a Domain-specific LLM Extractor	提出D-Pruner，用于领域特定大语言模型的双重剪枝压缩，提升效率。	large language model	✅
14	Automatic Generation of Model and Data Cards: A Step Towards Responsible AI	提出CardGen流水线，自动生成模型和数据卡，提升负责任AI文档的完整性和客观性。	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
15	Linearizing Large Language Models	提出SUPRA方法，以低成本将预训练Transformer LLM转化为线性RNN，提升推理效率。	Mamba large language model	✅
16	HC$^2$L: Hybrid and Cooperative Contrastive Learning for Cross-lingual Spoken Language Understanding	提出混合协同对比学习(HC$^2$L)用于跨语言口语理解	contrastive learning
17	For the Misgendered Chinese in Gender Bias Research: Multi-Task Learning with Knowledge Distillation for Pinyin Name-Gender Prediction	提出基于多任务学习与知识蒸馏的拼音姓名性别预测方法，提升中文姓名性别识别准确率。	distillation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
18	Are EEG-to-Text Models Working?	揭示脑电到文本模型评估中的缺陷：过度依赖Teacher-Forcing和缺乏噪声基准	open-vocabulary open vocabulary	✅
19	LIVE: LaTex Interactive Visual Editing	提出LIVE：一种用于LaTeX文档中交互式可视化元素的创新设计方法	NeRF

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
20	Enhancing Traffic Prediction with Textual Data Using Large Language Models	利用大语言模型处理文本信息，增强时空交通预测能力	spatiotemporal large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页