cs.CL（2025-07-28）

📊 共 18 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) (15 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3)

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

#题目一句话要点标签🔗⭐
1 AQUA: A Large Language Model for Aquaculture & Fisheries AQUA：面向水产养殖与渔业的大型语言模型 large language model
2 Memorization in Fine-Tuned Large Language Models 研究微调LLM中的记忆机制，揭示性能与隐私的权衡，为医疗领域应用提供指导。 large language model
3 Ontology-Enhanced Knowledge Graph Completion using Large Language Models 提出OL-KGC：一种本体增强的LLM知识图谱补全方法 large language model
4 Do Large Language Models Understand Morality Across Cultures? 评估大型语言模型在跨文化道德理解上的能力与偏差 large language model
5 Leveraging Open-Source Large Language Models for Clinical Information Extraction in Resource-Constrained Settings 提出开放源代码大语言模型以解决临床信息提取问题 large language model
6 Automating Thematic Review of Prevention of Future Deaths Reports: Replicating the ONS Child Suicide Study using Large Language Models 利用大型语言模型自动化死因预防报告的主题审查，复现ONS儿童自杀研究。 large language model
7 StructText: A Synthetic Table-to-Text Approach for Benchmark Generation with Multi-Dimensional Evaluation StructText：一种合成表格到文本的方法，用于生成具有多维度评估的基准数据集。 large language model
8 Enhancing Hallucination Detection via Future Context 利用未来上下文增强大型语言模型幻觉检测 large language model
9 Soft Injection of Task Embeddings Outperforms Prompt-Based In-Context Learning 提出软注入任务嵌入方法，超越提示学习并降低计算成本 large language model
10 Enhancing Project-Specific Code Completion by Inferring Internal API Information 提出一种推断内部API信息的方法，增强项目特定代码补全能力 large language model
11 Latent Inter-User Difference Modeling for LLM Personalization 提出DEP框架，通过建模用户潜在差异实现LLM个性化 large language model ✅
12 When Scale Meets Diversity: Evaluating Language Models on Fine-Grained Multilingual Claim Verification 多语言细粒度声明验证：小模型XLM-R超越大型语言模型 large language model
13 Geometric-Mean Policy Optimization 提出几何均值策略优化以解决GRPO不稳定问题 large language model ✅
14 ZSE-Cap: A Zero-Shot Ensemble for Image Retrieval and Prompt-Guided Captioning ZSE-Cap：一种用于图像检索和提示引导字幕生成的零样本集成方法 foundation model ✅
15 SAND-Math: Using LLMs to Generate Novel, Difficult and Useful Mathematics Questions and Answers SAND-Math：利用LLM生成新颖、困难且有用的数学问题与答案，提升数学推理能力。 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🔗⭐
16 Investigating Structural Pruning and Recovery Techniques for Compressing Multimodal Large Language Models: An Empirical Study 研究多模态大语言模型的结构化剪枝与恢复技术，实现高效压缩。 distillation large language model multimodal
17 Mind the Gap: Conformative Decoding to Improve Output Diversity of Instruction-Tuned Large Language Models 提出Conformative Decoding，提升指令调优大语言模型生成文本的多样性 DPO large language model
18 On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey 综述：预训练语言模型在通用文本嵌入中的作用 contrastive learning multimodal

⬅️ 返回 cs.CL 首页 · 🏠 返回主页