cs.CL（2025-08-31）

📊 共 12 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱四：生成式动作 (Generative Motion) (1)

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

#题目一句话要点标签🔗⭐
1 MedCOD: Enhancing English-to-Spanish Medical Translation of Large Language Models Using Enriched Chain-of-Dictionary Framework 提出MedCOD框架以提升医学英语到西班牙语翻译质量 large language model
2 Energy Landscapes Enable Reliable Abstention in Retrieval-Augmented Large Language Models for Healthcare 提出能量基础模型以解决医疗领域检索增强生成系统的可靠性问题 large language model
3 Exploring and Mitigating Fawning Hallucinations in Large Language Models 提出协作对比解码以缓解大型语言模型中的谄媚幻觉问题 large language model
4 Structure and Destructure: Dual Forces in the Making of Knowledge Engines 提出结构与解构双重力量以构建知识引擎 large language model
5 Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction 提出动态构建知识图谱以提升LLM的事实准确性 large language model
6 LLM Encoder vs. Decoder: Robust Detection of Chinese AI-Generated Text with LoRA 提出基于LoRA的解码器模型以提高中文AI生成文本检测的鲁棒性 large language model
7 Learning to Shop Like Humans: A Review-driven Retrieval-Augmented Recommendation Framework with LLMs 提出RevBrowse框架以解决LLM推荐中的评论整合问题 large language model
8 CE-Bench: Towards a Reliable Contrastive Evaluation Benchmark of Interpretability of Sparse Autoencoders 提出CE-Bench以解决稀疏自编码器可解释性评估问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
9 Text Reinforcement for Multimodal Time Series Forecasting 提出文本强化模型以提升多模态时间序列预测性能 reinforcement learning multimodal
10 RPRO: Ranked Preference Reinforcement Optimization for Enhancing Medical QA and Diagnostic Reasoning 提出RPRO以解决医疗问答中的推理准确性问题 reinforcement learning large language model chain-of-thought
11 Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text Embeddings 提出多粒度硬负样本合成与锚标记感知池化以提升文本嵌入 contrastive learning curriculum learning large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
12 Reward-Weighted Sampling: Enhancing Non-Autoregressive Characteristics in Masked Diffusion LLMs 提出奖励加权采样以增强掩蔽扩散模型的非自回归特性 MDM large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页