cs.CL（2024-02-02）

📊 共 26 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) (19 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (7)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#题目一句话要点标签🔗⭐
1 Continual Learning for Large Language Models: A Survey 提出多阶段分类方案以解决大语言模型的持续学习问题 large language model
2 Speech foundation models in healthcare: Effect of layer selection on pathological speech feature prediction 通过层选择优化基础模型以提升病理语音特征预测 foundation model
3 Leveraging Large Language Models for Analyzing Blood Pressure Variations Across Biological Sex from Scientific Literature 利用大型语言模型分析生物性别间血压变化 large language model
4 Building Guardrails for Large Language Models 提出系统化方法构建大型语言模型的安全防护措施 large language model
5 K-Level Reasoning: Establishing Higher Order Beliefs in Large Language Models for Strategic Reasoning 提出K级推理框架以解决大型语言模型的战略推理问题 large language model
6 KB-Plugin: A Plug-and-play Framework for Large Language Models to Induce Programs over Low-resourced Knowledge Bases 提出KB-Plugin框架以解决低资源知识库的程序诱导问题 large language model ✅
7 Style Vectors for Steering Generative Large Language Model 提出风格向量以引导生成大型语言模型的输出 large language model
8 A Comparative Analysis of Conversational Large Language Models in Knowledge-Based Text Generation 通过少量提示和后处理提升对话大语言模型的知识文本生成能力 large language model
9 DTS-SQL: Decomposed Text-to-SQL with Small Large Language Models 提出DTS-SQL以解决小型语言模型在文本到SQL任务中的性能不足问题 large language model
10 Can LLMs perform structured graph reasoning? 提出图推理任务以评估大型语言模型的结构化推理能力 large language model chain-of-thought
11 PiCO: Peer Review in LLMs based on the Consistency Optimization 提出基于一致性优化的LLM同行评审方法以提升评估准确性 large language model
12 LoTR: Low Tensor Rank Weight Adaptation 提出LoTR以实现高效的低秩权重适应 large language model
13 Reasoning Capacity in Multi-Agent Systems: Limitations, Challenges and Human-Centered Solutions 提出推理能力概念以解决多智能体系统中的优化与评估问题 large language model
14 LitLLM: A Toolkit for Scientific Literature Review 提出LitLLM工具包以解决科学文献综述的自动化问题 large language model
15 TravelPlanner: A Benchmark for Real-World Planning with Language Agents 提出TravelPlanner以解决复杂旅行规划问题 large language model
16 AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback 提出AMOR框架以构建适应性模块化知识代理 large language model ✅
17 LLM-based NLG Evaluation: Current Status and Challenges 提出基于LLM的NLG评估方法以解决传统评估不足问题 large language model
18 CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks 提出CorpusLM以解决知识密集型任务中的信息检索与生成问题 large language model
19 LLM-Detector: Improving AI-Generated Chinese Text Detection with Open-Source LLM Instruction Tuning 提出LLM-Detector以解决AI生成中文文本检测问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
20 The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models 提出RL/LLM分类树以探讨强化学习与大语言模型的协同作用 reinforcement learning reward shaping large language model
21 MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models 提出MAGDi以提高小型语言模型的推理能力 distillation large language model
22 StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback 提出StepCoder以解决复杂代码生成中的探索挑战 reinforcement learning large language model
23 Distilling LLMs' Decomposition Abilities into Compact Language Models 通过蒸馏LLM的分解能力提升紧凑语言模型的推理能力 reinforcement learning offline reinforcement learning large language model
24 Code Representation Learning At Scale 提出大规模代码表示学习方法以提升代码生成性能 representation learning contrastive learning
25 LiPO: Listwise Preference Optimization through Learning-to-Rank 提出LiPO框架以优化语言模型的偏好对齐问题 reinforcement learning RLHF DPO
26 In-Context Learning for Few-Shot Nested Named Entity Recognition 提出一种创新的ICL框架以解决少样本嵌套命名实体识别问题 representation learning contrastive learning

⬅️ 返回 cs.CL 首页 · 🏠 返回主页