cs.CL（2024-02-06）

📊 共 27 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (21 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (21 篇)

#题目一句话要点标签🔗⭐
1 Identifying Reasons for Contraceptive Switching from Real-World Data Using Large Language Models 利用大型语言模型识别避孕药物更换原因 large language model ✅
2 Large Language Models As MOOCs Graders 利用大型语言模型改进MOOC作业评分 large language model chain-of-thought
3 Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning 提出直接-间接推理方法以提升大语言模型的推理能力 large language model chain-of-thought
4 DFA-RAG: Conversational Semantic Router for Large Language Model with Definite Finite Automaton 提出DFA-RAG以解决对话生成中的合规性问题 large language model
5 Scaling Laws for Downstream Task Performance of Large Language Models 研究大语言模型下游任务性能的扩展规律 large language model
6 The Use of a Large Language Model for Cyberbullying Detection 利用大型语言模型检测网络欺凌问题 large language model
7 ANLS* -- A Universal Document Processing Metric for Generative Large Language Models 提出ANLS*以解决生成大语言模型评估问题 large language model ✅
8 Leveraging Large Language Models for Hybrid Workplace Decision Support 提出基于大语言模型的混合工作场所决策支持系统 large language model
9 Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning 提出OPPU以解决大语言模型个性化定制问题 large language model
10 The World of Generative AI: Deepfakes and Large Language Models 探讨生成性人工智能中的深伪技术与大型语言模型的相互关系 large language model
11 Measuring Implicit Bias in Explicitly Unbiased Large Language Models 提出新方法以测量大型语言模型中的隐性偏见 large language model
12 Can Large Language Models Detect Rumors on Social Media? 提出LeRuD以解决社交媒体谣言检测问题 large language model
13 Rethinking Skill Extraction in the Job Market Domain using Large Language Models 利用大语言模型重新思考职业市场中的技能提取 large language model
14 Professional Agents -- Evolving Large Language Models into Autonomous Experts with Human-Level Competencies 提出专业代理框架以实现自主智能体的专业能力 large language model
15 Partially Recentralization Softmax Loss for Vision-Language Models Robustness 提出部分重中心化Softmax损失以增强多模态模型的鲁棒性 large language model multimodal
16 LegalLens: Leveraging LLMs for Legal Violation Identification in Unstructured Text 提出LegalLens以解决法律文本中的违规识别问题 large language model
17 Exposing propaganda: an analysis of stylistic cues comparing human annotations and machine classification 提出PPN数据集以分析宣传语言的风格特征 multimodal
18 Systematic Biases in LLM Simulations of Debates 揭示大型语言模型在辩论模拟中的系统性偏差 large language model
19 Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs 系统分析数据污染与评估不当行为在闭源LLMs中的影响 large language model
20 AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls 提出AnyTool以优化大规模API调用的工具使用 large language model ✅
21 LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K 提出LV-Eval以解决长上下文基准评估不足的问题 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
22 DistiLLM: Towards Streamlined Distillation for Large Language Models 提出DistiLLM以解决大语言模型蒸馏效率低下问题 distillation large language model instruction following
23 Iterative Prompt Refinement for Radiation Oncology Symptom Extraction Using Teacher-Student Large Language Models 提出教师-学生架构以改善放射肿瘤学症状提取 teacher-student large language model
24 Personalized Language Modeling from Personalized Human Feedback 提出个性化RLHF框架以解决多样化用户偏好问题 reinforcement learning RLHF large language model ✅
25 Detecting Mode Collapse in Language Models via Narration 通过叙述检测语言模型中的模式崩溃现象 reinforcement learning RLHF large language model

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
26 Beyond Lines and Circles: Unveiling the Geometric Reasoning Gap in Large Language Models 提出多智能体系统以解决大语言模型的几何推理问题 spatial relationship large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
27 Listen, Chat, and Remix: Text-Guided Soundscape Remixing for Enhanced Auditory Experience 提出LCR以实现基于文本的音景重混合控制 open-vocabulary open vocabulary large language model ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页