cs.CL（2025-04-25）

📊 共 18 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (15 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#	题目	一句话要点	标签	🔗	⭐
1	A Method for the Architecture of a Medical Vertical Large Language Model Based on Deepseek R1	提出一种基于Deepseek R1的轻量级医疗垂直大语言模型架构，解决资源受限场景下的部署难题。	large language model foundation model
2	Random-Set Large Language Models	提出随机集大语言模型(RSLLM)以量化LLM的不确定性并提升答案正确性。	large language model
3	Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review	系统性评测大语言模型不确定性度量与缓解方法，并提出基准	large language model
4	RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models	RAG大语言模型并非更安全：检索增强生成框架的安全分析	large language model
5	Memory Reviving, Continuing Learning and Beyond: Evaluation of Pre-trained Encoders and Decoders for Multimodal Machine Translation	系统评估预训练编码器和解码器在多模态机器翻译中的作用与影响	multimodal
6	Investigating Co-Constructive Behavior of Large Language Models in Explanation Dialogues	研究大型语言模型在解释对话中的协同构建能力，探索其在可解释AI中的应用	large language model
7	TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generation	TRACE：提出一种基于概率推理的可控语言生成框架，提升生成质量与效率。	large language model	✅
8	BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs	BitNet v2：利用Hadamard变换实现原生4比特激活的1比特LLM	large language model
9	One-Pass to Reason: Token Duplication and Block-Sparse Mask for Efficient Fine-Tuning on Multi-Turn Reasoning	提出一种基于Token复制和块稀疏掩码的单次推理微调方法，加速多轮对话LLM训练。	large language model	✅
10	Application and Optimization of Large Models Based on Prompt Tuning for Fact-Check-Worthiness Estimation	提出基于Prompt Tuning的大模型方法，用于提升事实核查价值评估的准确性	large language model
11	PropRAG: Guiding Retrieval with Beam Search over Proposition Paths	PropRAG：利用命题路径上的束搜索引导检索，提升多跳推理RAG性能	large language model
12	HRScene: How Far Are VLMs from Effective High-Resolution Image Understanding?	HRScene：构建高分辨率图像理解的综合评测基准，揭示VLMs的局限性	large language model
13	Auto-SLURP: A Benchmark Dataset for Evaluating Multi-Agent Frameworks in Smart Personal Assistant	Auto-SLURP：用于评估智能个人助理中多智能体框架的基准数据集。	large language model	✅
14	Comparative Study on the Discourse Meaning of Chinese and English Media in the Paris Olympics Based on LDA Topic Modeling Technology and LLM Prompt Engineering	基于LDA主题建模和LLM提示工程比较中英媒体对巴黎奥运会的叙事意义	large language model
15	Improving Language Model Personas via Rationalization with Psychological Scaffolds	提出PB&J框架，通过心理学支架增强语言模型的人格化，提升用户偏好预测。	chain-of-thought

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
16	DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models	DREAM：解耦多模态大语言模型的风险以增强安全对齐	reinforcement learning large language model multimodal	✅
17	Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning	Nemotron-Research-Tool-N1：通过强化推理探索工具使用语言模型	reinforcement learning large language model

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
18	Anti-adversarial Learning: Desensitizing Prompts for Large Language Models	提出PromptObfus，通过反对抗学习脱敏大语言模型提示词，保护用户隐私。	OMOMO large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页