cs.CL(2024-11-21)

📊 共 25 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 🔗2)

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

#题目一句话要点标签🔗
1 Evaluating the Robustness of Analogical Reasoning in Large Language Models 评估大语言模型在类比推理中对变体的鲁棒性,揭示其脆弱性。 large language model
2 Robust Detection of Watermarks for Large Language Models Under Human Edits 提出Tr-GoF方法,解决人工编辑下大语言模型水印鲁棒检测问题 large language model
3 Exploring Accuracy-Fairness Trade-off in Large Language Models 提出多目标进化学习以解决大型语言模型的准确性与公平性平衡问题 large language model
4 Interactive and Expressive Code-Augmented Planning with Large Language Models 提出REPL-Plan,利用代码增强的大语言模型进行交互式和表达性规划 large language model
5 Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective 利用知识图谱缓解大语言模型幻觉问题:NLP视角综述 large language model
6 PIORS: Personalized Intelligent Outpatient Reception based on Large Language Model with Multi-Agents Medical Scenario Simulation 提出PIORS:基于大语言模型与多智能体医疗场景模拟的个性化智能门诊接待系统 large language model
7 Towards a Middleware for Large Language Models 面向企业级LLM部署,提出一种中间件架构以实现自主可控的LLM服务 large language model
8 Learning from "Silly" Questions Improves Large Language Models, But Only Slightly 利用“愚蠢”问题提升大语言模型性能,但效果有限 large language model
9 Lost in Inference: Rediscovering the Role of Natural Language Inference for Large Language Models 利用自然语言推理任务评估和区分大型语言模型 large language model
10 DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization 提出DRPruning,通过分布鲁棒优化实现高效的大语言模型剪枝 large language model
11 SemiKong: Curating, Training, and Evaluating A Semiconductor Industry-Specific Large Language Model SemiKong:构建、训练和评估半导体行业专用大语言模型 large language model
12 Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models 利用稀疏自编码器发现语言模型中的知识感知机制与幻觉现象 large language model
13 OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs OpenScholar:利用检索增强的语言模型合成科学文献 large language model
14 NewsInterview: a Dataset and a Playground to Evaluate LLMs' Ground Gap via Informational Interviews NewsInterview:构建新闻访谈数据集与模拟环境,评估LLM在信息获取中的知识盲区 large language model
15 Enhancing LLMs for Power System Simulations: A Feedback-driven Multi-agent Framework 提出反馈驱动的多智能体框架,增强LLM在电力系统仿真中的应用 large language model
16 UnifiedCrawl: Aggregated Common Crawl for Affordable Adaptation of LLMs on Low-Resource Languages UnifiedCrawl:利用聚合Common Crawl数据低成本适配低资源语言LLM large language model
17 Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning Star-Agents:利用LLM智能体自动优化指令微调数据 large language model
18 Lightweight Safety Guardrails Using Fine-tuned BERT Embeddings 提出基于微调BERT嵌入的轻量级安全防护栏,降低LLM部署成本。 large language model
19 Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training Velocitune:一种基于学习速度的动态领域重加权方法,用于持续预训练。 large language model
20 Efficient Aspect-Based Summarization of Climate Change Reports with Small Language Models 提出气候变化报告的基于方面摘要数据集,并验证小型语言模型在该任务上的有效性。 large language model
21 InstCache: A Predictive Cache for LLM Serving InstCache:一种用于LLM服务的预测性缓存机制,提升指令缓存命中率。 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 Understanding World or Predicting Future? A Comprehensive Survey of World Models 世界模型综述:理解世界表征与预测未来动态 world model large language model multimodal
23 From Intents to Conversations: Generating Intent-Driven Dialogues with Contrastive Learning for Multi-Turn Classification 提出Chain-of-Intent框架,结合HMM和LLM生成意图驱动的对话,并用对比学习提升多轮意图分类。 contrastive learning large language model
24 BEST-STD: Bidirectional Mamba-Enhanced Speech Tokenization for Spoken Term Detection 提出BEST-STD,利用双向Mamba增强语音令牌化,提升口语词检测性能。 Mamba state space model
25 Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions Marco-o1:面向开放式解决方案的开放推理模型 reinforcement learning chain-of-thought

⬅️ 返回 cs.CL 首页 · 🏠 返回主页