cs.CL（2024-10-26）

📊 共 12 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) 支柱一：机器人控制 (Robot Control) (1)

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

#题目一句话要点标签🔗⭐
1 A Survey of Large Language Models for Arabic Language and its Dialects 综述性研究：面向阿拉伯语及其方言的大型语言模型 large language model
2 Beyond Fine-Tuning: Effective Strategies for Mitigating Hallucinations in Large Language Models for Data Analytics 针对数据分析，提出多种策略以有效缓解大语言模型中的幻觉问题 large language model
3 Mathematical Derivation Graphs: A Relation Extraction Task in STEM Manuscripts 提出数学推导图数据集MDGD，用于STEM文献中公式间关系抽取任务 large language model
4 Dynamic layer selection in decoder-only transformers 研究decoder-only Transformer的动态层选择，实现高效自然语言生成。 large language model
5 Think Carefully and Check Again! Meta-Generation Unlocking LLMs for Low-Resource Cross-Lingual Summarization 提出SITR方法以解决低资源语言的跨语言摘要问题 large language model
6 Generative linguistics contribution to artificial intelligence: Where this contribution lies? 探讨生成语言学对人工智能的贡献：基于乔姆斯基学派的视角 large language model
7 DAWN-ICL: Strategic Planning of Problem-solving Trajectories for Zero-Shot In-Context Learning 提出DAWN-ICL以解决零样本上下文学习中的问题规划挑战 large language model ✅
8 Reasoning or a Semblance of it? A Diagnostic Study of Transitive Reasoning in LLMs 通过操纵事实，诊断LLaMA 2和Flan-T5在传递推理上的能力差异 large language model
9 UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers 提出UniHGKR，统一指令感知的异构知识检索器，提升开放域问答性能。 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 Fast Best-of-N Decoding via Speculative Rejection 提出Speculative Rejection算法，加速Best-of-N解码，提升LLM推理时对齐效率。 PPO DPO large language model
11 Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent Discovery 提出伪标签增强的原型对比学习方法，用于统一意图发现。 contrastive learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
12 Vulnerability of LLMs to Vertically Aligned Text Manipulations 揭示LLM在垂直对齐文本输入下的脆弱性，并分析其内在原因 manipulation large language model chain-of-thought

⬅️ 返回 cs.CL 首页 · 🏠 返回主页