cs.CL（2025-05-21）

📊 共 10 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs	提出KnowRecall和VisRecall基准以解决多语言一致性问题	large language model multimodal
2	Are LLMs reliable? An exploration of the reliability of large language models in clinical note generation	评估大型语言模型在临床笔记生成中的可靠性	large language model
3	Can Large Language Models Understand Internet Buzzwords Through User-Generated Content	提出CHEER数据集与RESS方法以提升大语言模型对网络流行词的理解能力	large language model	✅
4	Lost in Benchmarks? Rethinking Large Language Model Benchmarking with Item Response Theory	提出PSN-IRT框架以提升大语言模型基准评估的有效性	large language model
5	Effective and Efficient Schema-aware Information Extraction Using On-Device Large Language Models	提出DLISC以解决资源受限设备上的信息提取问题	large language model
6	Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective	提出扩散语言模型以解决自回归模型在文本嵌入中的局限性	large language model instruction following
7	Towards Spoken Mathematical Reasoning: Benchmarking Speech-based Models over Multi-faceted Math Problems	提出Spoken-MQA基准以评估语音模型的数学推理能力	large language model multimodal
8	MAS-ZERO: Designing Multi-Agent Systems with Zero Supervision	提出MAS-ZERO以解决多智能体系统设计中的监督依赖问题	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	🔗	⭐
9	DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data	提出DISCO以解决不平衡数据下的强化学习问题	reinforcement learning policy learning consistency policy	✅
10	Self-GIVE: Associative Thinking from Limited Structured Knowledge for Enhanced Large Language Model Reasoning	提出Self-GIVE以解决大语言模型推理中的关联思维问题	reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页