cs.CL（2025-04-11）

📊 共 19 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) (16 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#题目一句话要点标签🔗⭐
1 LLMTaxo: Leveraging Large Language Models for Constructing Taxonomy of Factual Claims from Social Media LLMTaxo：利用大型语言模型构建社交媒体事实性声明分类体系 large language model
2 Fast-Slow-Thinking: Complex Task Solving with Large Language Models 提出Fast-Slow-Thinking方法，提升大语言模型在复杂任务中的问题解决能力 large language model
3 Beyond Self-Reports: Multi-Observer Agents for Personality Assessment in Large Language Models 提出多观察者框架，用于更可靠地评估大型语言模型的人格特质 large language model
4 Large Language Models Could Be Rote Learners 提出TrinEval框架，用于解耦大语言模型中的死记硬背与能力学习 large language model
5 A Fully Automated Pipeline for Conversational Discourse Annotation: Tree Scheme Generation and Labeling with Large Language Models 提出一种全自动对话语篇标注流程，利用大语言模型生成树形结构并进行标注。 large language model
6 Large Language Model Empowered Recommendation Meets All-domain Continual Pre-Training 提出CPRec，通过全域持续预训练提升LLM在推荐系统中的性能。 large language model
7 Spatial Audio Processing with Large Language Model on Wearable Devices 提出SING：在可穿戴设备上利用LLM进行空间音频处理，提升语音理解能力 large language model
8 ELSA: A Style Aligned Dataset for Emotionally Intelligent Language Generation ELSA：一种风格对齐的情感智能语言生成数据集，提升情感控制和风格适应能力。 large language model
9 Generating Planning Feedback for Open-Ended Programming Exercises with LLMs 利用大型语言模型为开放式编程练习生成规划反馈 large language model
10 Cross-Document Cross-Lingual NLI via RST-Enhanced Graph Fusion and Interpretability Prediction 提出RST增强图融合和可解释性预测的跨文档跨语言NLI方法，并构建高质量数据集。 large language model ✅
11 The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generation 探索RAG框架下的公平性问题，并提出FairFT和FairFilter方法缓解小规模LLM中的不公平现象。 large language model
12 LLMs as Span Annotators: A Comparative Study of LLMs and Humans 研究LLM作为文本片段标注器的能力，对比其与人类标注者的表现 large language model
13 Analyzing 16,193 LLM Papers for Fun and Profits 分析16193篇LLM论文，揭示计算机科学研究领域的发展趋势与机构贡献。 large language model
14 UoB-NLP at SemEval-2025 Task 11: Leveraging Adapters for Multilingual and Cross-Lingual Emotion Detection 利用Adapters进行多语和跨语情感检测，提升低资源语言性能 large language model
15 Evaluating the Bias in LLMs for Surveying Opinion and Decision Making in Healthcare 利用LLM评估医疗决策中的偏差：对比真实调研与生成代理 large language model
16 Harnessing the Unseen: The Hidden Influence of Intrinsic Knowledge in Long-Context Language Models 长文本模型中固有知识影响被忽视，提出混合检索评估方法并验证Qwen-2.5的优越性。 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🔗⭐
17 Playpen: An Environment for Exploring Learning Through Conversational Interaction Playpen：一个通过对话交互探索学习的环境，用于LLM的后训练。 reinforcement learning imitation learning DPO
18 A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data Synthesis 提出GRA框架，通过协同小LLM实现与大LLM相当的数据合成能力 distillation large language model ✅

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
19 TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planning TP-RAG：提出时空感知旅行规划的检索增强大语言模型基准测试与EvoRAG优化框架 spatiotemporal large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页