cs.CL（2023-11-27）

📊 共 18 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (15 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#题目一句话要点标签🔗⭐
1 Vision Enhancing LLMs: Empowering Multimodal Knowledge Storage and Sharing in LLMs 提出MKS2以增强大语言模型的多模态知识存储与共享能力 large language model multimodal instruction following ✅
2 MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI 提出MMMU基准以评估多模态模型在多学科推理中的表现 foundation model multimodal
3 MEDITRON-70B: Scaling Medical Pretraining for Large Language Models 提出MEDITRON-70B以解决医疗领域大规模语言模型的访问问题 large language model
4 SpotServe: Serving Generative Large Language Models on Preemptible Instances 提出SpotServe以解决生成大语言模型的低成本服务问题 large language model
5 Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucination 实证研究大型语言模型在金融领域的幻觉问题 large language model
6 Releasing the CRaQAn (Coreference Resolution in Question-Answering): An open-source dataset and dataset creation methodology using instruction-following models 提出CRaQAn数据集以解决问答中的共指解析问题 instruction following
7 YUAN 2.0: A Large Language Model with Localized Filtering-based Attention 提出YUAN 2.0以提升大规模语言模型的性能与效率 large language model
8 Optimizing and Fine-tuning Large Language Model for Urban Renewal 提出联合微调方法以优化城市更新领域的大语言模型 large language model
9 DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer 提出DP-OPT以解决大语言模型隐私保护的提示工程问题 large language model ✅
10 Novel Preprocessing Technique for Data Embedding in Engineering Code Generation Using Large Language Model 提出新型预处理技术以提升工程代码生成的性能 large language model
11 Justifiable Artificial Intelligence: Engineering Large Language Models for Legal Applications 提出可辩护的人工智能以解决法律领域信任问题 large language model
12 FreeAL: Towards Human-Free Active Learning in the Era of Large Language Models 提出FreeAL以解决大语言模型时代的无人工主动学习问题 large language model ✅
13 MoDS: Model-oriented Data Selection for Instruction Tuning 提出MoDS以解决指令调优中的数据选择问题 large language model instruction following
14 Real Customization or Just Marketing: Are Customized Versions of Chat GPT Useful? 评估定制化GPT在商业统计教学中的有效性 large language model
15 The effect of source disclosure on evaluation of AI-generated messages: A two-part study 研究源披露对AI生成消息评估的影响 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🔗⭐
16 WorldSense: A Synthetic Benchmark for Grounded Reasoning in Large Language Models 提出WorldSense基准以评估大型语言模型的推理能力 world model world models large language model
17 BioLORD-2023: Semantic Textual Representations Fusing LLM and Clinical Knowledge Graph Insights 提出BioLORD-2023以提升生物医学语义表示能力 representation learning contrastive learning distillation
18 Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval 提出ABEL以解决零-shot密集检索的适应性问题 distillation ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页