cs.CL（2024-11-02）

📊 共 11 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Can Multimodal Large Language Model Think Analogically?	探索多模态大语言模型在类比推理中的能力，并提出相应方法。	large language model multimodal
2	Arena-Lite: Efficient and Reliable Large Language Model Evaluation via Tournament-Based Direct Comparisons	Arena-Lite：基于锦标赛直接比较的高效可靠大语言模型评测方法	large language model	✅
3	Transfer Learning for Finetuning Large Language Models	提出基于迁移学习的大语言模型微调方法，提升微调效率与效果。	large language model
4	Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Models	提出字典插入提示（DIP）方法，提升多语言大模型在非英语推理任务上的性能。	large language model
5	Diversidade linguística e inclusão digital: desafios para uma ia brasileira	探讨生成式AI背景下巴西语言多样性面临的数字包容性挑战	large language model
6	Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks	提出Swan系列阿拉伯语嵌入模型和ArabicMTEB基准，提升跨语种、方言和文化场景下的性能。	large language model	✅
7	CmdCaliper: A Semantic-Aware Command-Line Embedding Model and Dataset for Security Research	提出CmdCaliper：一个用于安全研究的语义感知命令行嵌入模型与数据集	large language model
8	Self-Consistency Falls Short! The Adverse Effects of Positional Bias on Long-Context Problems	自洽性在长文本问题中失效：位置偏差的负面影响	large language model
9	TabVer: Tabular Fact Verification with Natural Logic	TabVer：利用自然逻辑进行表格型事实验证，提升可验证性。	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	TODO: Enhancing LLM Alignment with Ternary Preferences	提出TODO算法，利用三元偏好优化LLM对齐，提升模型性能。	DPO direct preference optimization large language model	✅
11	PMoL: Parameter Efficient MoE for Preference Mixing of LLM Alignment	提出PMoL：一种参数高效的MoE架构，用于LLM对齐中的偏好混合	reinforcement learning RLHF large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页