cs.CL（2024-12-14）

📊 共 13 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation 提出VisDoMRAG，利用多模态检索增强生成解决富视觉元素多文档问答难题。 large language model multimodal chain-of-thought
2 Large Language Models for Medical Forecasting -- Foresight 2 Foresight 2：通过医院数据微调的大语言模型，用于医疗预测。 large language model
3 Tokens, the oft-overlooked appetizer: Large language models, the distributional hypothesis, and meaning 关注Tokenization对LLM认知的影响，揭示其在语义和偏差引入中的作用 large language model
4 Rethinking Chain-of-Thought from the Perspective of Self-Training 从自训练视角重新审视思维链，提出自适应迭代CoT框架 chain-of-thought
5 Streamlining Systematic Reviews: A Novel Application of Large Language Models 提出基于大语言模型的系统综述自动化方法，显著提升文献筛选效率。 large language model
6 Thinking with Knowledge Graphs: Enhancing LLM Reasoning Through Structured Data 提出基于知识图谱的LLM增强方法，提升复杂推理能力并减少幻觉 large language model
7 HITgram: A Platform for Experimenting with n-gram Language Models HITgram：一个轻量级的n-gram语言模型实验平台，适用于资源受限环境。 large language model
8 Accelerating Retrieval-Augmented Generation 设计智能知识存储IKS，加速检索增强生成RAG中的精确近邻搜索。 large language model
9 Learning to Verify Summary Facts with Fine-Grained LLM Feedback 提出FineSumFact数据集，利用LLM反馈提升摘要事实核查模型性能。 large language model ✅
10 Can LLMs Help Create Grammar?: Automating Grammar Creation for Endangered Languages with In-Context Learning 利用上下文学习，LLM助力濒危语言的自动化语法生成 large language model
11 Inference Scaling for Bridging Retrieval and Augmented Generation 提出Mixture-of-Intervention (MOI)方法，通过推理缩放缓解RAG中的生成器偏差问题。 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🔗⭐
12 Chasing Progress, Not Perfection: Revisiting Strategies for End-to-End LLM Plan Generation 提出端到端LLM规划生成策略以解决规划能力不足问题 reinforcement learning large language model chain-of-thought
13 WEPO: Web Element Preference Optimization for LLM-based Web Navigation WEPO：通过网页元素偏好优化提升LLM在网页导航中的性能 preference learning DPO direct preference optimization

⬅️ 返回 cs.CL 首页 · 🏠 返回主页