cs.CL（2024-03-07）

📊 共 27 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) (24 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (24 篇)

#题目一句话要点标签🔗⭐
1 Exploring LLM-based Agents for Root Cause Analysis 提出基于LLM的代理以解决根本原因分析的局限性 large language model
2 MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation 提出MEIT框架以解决ECG报告生成问题 large language model multimodal
3 Bridging Text and Molecule: A Survey on Multimodal Frameworks for Molecule 提出多模态框架以联合建模分子与文本知识 large language model multimodal
4 Yi: Open Foundation Models by 01.AI 提出Yi模型系列以提升多模态语言处理能力 foundation model multimodal
5 Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification 提出基于令牌级不确定性量化的事实检查方法以解决LLM输出的虚假信息问题 large language model
6 Where does In-context Translation Happen in Large Language Models 提出层级掩蔽实验以识别大语言模型中的翻译任务识别点 large language model
7 Measuring Meaning Composition in the Human Brain with Composition Scores from Large Language Models 提出Composition Score以量化人脑中的意义组合过程 large language model
8 Large Language Models are In-Context Molecule Learners 提出ICMA以解决大语言模型在分子文本对齐中的挑战 large language model
9 Few shot chain-of-thought driven reasoning to prompt LLMs for open ended medical question answering 提出基于链式推理的少量样本医学问答方法 chain-of-thought
10 Chain of Thought Explanation for Dialogue State Tracking 提出Chain-of-Thought-Explanation模型以提升对话状态跟踪精度 chain-of-thought
11 Self-Evaluation of Large Language Model based on Glass-box Features 提出基于玻璃盒特征的自我评估方法以提升大型语言模型的评估能力 large language model
12 Aligners: Decoupling LLMs and Alignment 提出Aligners模型以解耦大语言模型与对齐问题 large language model instruction following
13 LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error 提出模拟试错方法以提升工具学习的准确性 large language model
14 Telecom Language Models: Must They Be Large? 提出Phi-2以解决电信领域小型语言模型的效率问题 large language model
15 Membership Inference Attacks and Privacy in Topic Modeling 提出针对主题建模的成员推断攻击以解决隐私问题 large language model
16 Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks 提出语法感知中间填充基准以评估大型语言模型 large language model ✅
17 ECLM: Entity Level Language Model for Spoken Language Understanding with Chain of Intent 提出ECLM框架以解决口语理解中的意图识别问题 large language model ✅
18 Low-Resource Court Judgment Summarization for Common Law Systems 提出CLSum数据集以解决多法域判决摘要生成问题 large language model
19 Acceleron: A Tool to Accelerate Research Ideation 提出Acceleron以解决研究构思阶段工具匮乏问题 large language model
20 TEGEE: Task dEfinition Guided Expert Ensembling for Generalizable and Few-shot Learning 提出TEGEE以解决任务定义提取与学习效率问题 large language model
21 Regression-aware Inference with LLMs 提出回归感知推理方法以优化LLM的输出 large language model
22 Evaluating Biases in Context-Dependent Health Questions 研究大型语言模型在医疗领域的偏见问题 large language model
23 ProMoAI: Process Modeling with Generative AI ProMoAI工具通过生成式AI自动生成和优化流程模型 large language model
24 Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders 提出意图语义工具包以解决意图编码器的语义理解问题 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🔗⭐
25 Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy 提出Proxy-RLHF以降低大语言模型对齐的计算成本 reinforcement learning RLHF large language model
26 MedFLIP: Medical Vision-and-Language Self-supervised Fast Pre-Training with Masked Autoencoder 提出MedFLIP以解决医学图像分析中的数据稀缺问题 representation learning masked autoencoder MAE
27 UltraWiki: Ultra-fine-grained Entity Set Expansion with Negative Seed Entities 提出UltraWiki以解决超细粒度实体集扩展问题 contrastive learning chain-of-thought

⬅️ 返回 cs.CL 首页 · 🏠 返回主页