cs.CL（2025-04-27）

📊 共 13 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) (11 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Hallucinations and Key Information Extraction in Medical Texts: A Comprehensive Assessment of Open-Source Large Language Models	评估开源大语言模型在医疗文本关键信息抽取和幻觉问题上的表现	large language model
2	BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese	BrowseComp-ZH：构建中文Web浏览能力评测基准，揭示LLM在中文信息检索与推理的不足。	large language model	✅
3	Efficient Reasoning for LLMs through Speculative Chain-of-Thought	提出SCoT以降低大型语言模型推理延迟	chain-of-thought	✅
4	VIST-GPT: Ushering in the Era of Visual Storytelling with LLMs?	VIST-GPT：利用大型多模态模型开启视觉故事讲述新纪元	multimodal visual grounding
5	Keep the General, Inject the Specific: Structured Dialogue Fine-Tuning for Knowledge Injection without Catastrophic Forgetting	提出结构化对话微调SDFT，解决视觉语言模型知识注入中的灾难性遗忘问题	multimodal chain-of-thought
6	Unified Multi-Task Learning & Model Fusion for Efficient Language Model Guardrailing	提出UniGuard，通过多任务学习和模型融合，高效保障语言模型安全。	large language model
7	ClimaEmpact: Domain-Aligned Small Language Models and Datasets for Extreme Weather Analytics	ClimaEmpact：提出领域对齐的小语言模型和数据集，用于极端天气分析	large language model
8	Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation	提出端到端检索增强生成框架，提升语音到语音对话模型性能。	large language model
9	AndroidGen: Building an Android Language Agent under Data Scarcity	AndroidGen：一种数据稀缺下构建Android语言代理的框架	large language model	✅
10	WuNeng: Hybrid State with Attention	WuNeng：融合RNN与注意力机制，提升大语言模型的表达能力和上下文连贯性	large language model
11	APE-Bench I: Towards File-level Automated Proof Engineering of Formal Math Libraries	提出APE-Bench I基准，用于评估LLM在形式化数学库文件级自动化证明工程中的能力。	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	🔗	⭐
12	SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning	提出SPC：通过对抗博弈演化自博弈评论家，提升LLM推理能力	reinforcement learning large language model chain-of-thought
13	Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generation	提出FedE4RAG框架，用于保护隐私的联邦检索增强生成，提升私有RAG系统性能。	distillation OMOMO large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页