cs.CL（2024-02-26）

📊 共 41 篇论文 | 🔗 9 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (36 🔗8) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (36 篇)

#题目一句话要点标签🔗⭐
1 Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space 重新审视多模态大语言模型中的跨模态投影角色 large language model multimodal ✅
2 Multi-Bit Distortion-Free Watermarking for Large Language Models 提出多比特无失真水印技术以增强大语言模型的水印能力 large language model
3 Integrating Large Language Models with Graphical Session-Based Recommendation 提出LLMGR框架以解决会话推荐系统中的图结构数据理解问题 large language model
4 Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models 提出更真实的评估方法以解决大语言模型价值观评估问题 large language model
5 A Comprehensive Evaluation of Quantization Strategies for Large Language Models 提出量化策略评估框架以优化大语言模型的性能 large language model
6 CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models 提出CodeChameleon框架以解决大语言模型的越狱问题 large language model
7 Aligning Large Language Models to a Domain-specific Graph Database for NL2GQL 提出一种方法将大型语言模型对齐于特定领域图数据库以解决NL2GQL问题 large language model
8 MoZIP: A Multilingual Benchmark to Evaluate Large Language Models in Intellectual Property 提出MoZIP基准以评估大语言模型在知识产权领域的表现 large language model ✅
9 Leveraging Large Language Models for Learning Complex Legal Concepts through Storytelling 利用大型语言模型通过讲故事学习复杂法律概念 large language model
10 Do Large Language Models Latently Perform Multi-Hop Reasoning? 探讨大型语言模型的潜在多跳推理能力 large language model
11 OncoGPT: A Medical Conversational Model Tailored with Oncology Domain Expertise on a Large Language Model Meta-AI (LLaMA) 提出OncoGPT以解决肿瘤学领域对话模型的准确性问题 large language model
12 Look Before You Leap: Towards Decision-Aware and Generalizable Tool-Usage for Large Language Models 提出DEER框架以解决开源LLM工具使用的灵活性与泛化性问题 large language model
13 Two-stage Generative Question Answering on Temporal Knowledge Graph Using Large Language Models 提出GenTKGQA框架以解决时间知识图谱问答问题 large language model
14 LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments 提出LLMArena以评估大语言模型在动态多智能体环境中的能力 large language model
15 Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models 提出语言激活概率熵方法以识别多语言模型中的语言特定神经元 large language model
16 RoCoIns: Enhancing Robustness of Large Language Models through Code-Style Instructions 提出代码风格指令以增强大语言模型的鲁棒性 large language model
17 Predicting Sustainable Development Goals Using Course Descriptions -- from LLMs to Conventional Foundation Models 利用课程描述预测可持续发展目标 foundation model
18 From RAGs to riches: Utilizing large language models to write documents for clinical trials 利用大型语言模型提升临床试验文档撰写效率 large language model
19 Data-free Weight Compress and Denoise for Large Language Models 提出无数据权重压缩与去噪方法以优化大型语言模型 large language model
20 SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection 提出SelectIT以解决LLMs指令调优数据选择问题 large language model foundation model ✅
21 Long-Context Language Modeling with Parallel Context Encoding 提出CEPE框架以扩展长上下文语言模型的处理能力 large language model instruction following
22 MindRef: Mimicking Human Memory for Hierarchical Reference Retrieval with Fine-Grained Location Awareness 提出MindRef以解决知识密集型任务中的参考文献检索问题 large language model
23 RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation 提出RepoAgent框架以解决代码文档生成不足问题 large language model ✅
24 Defending LLMs against Jailbreaking Attacks via Backtranslation 通过反向翻译防御大型语言模型的越狱攻击 large language model ✅
25 MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs 提出MathGenie以提升大型语言模型的数学推理能力 large language model
26 Cross-domain Chinese Sentence Pattern Parsing 提出基于自训练框架的跨域中文句型解析方法 large language model
27 Benchmarking LLMs on the Semantic Overlap Summarization Task 提出PrivacyPolicyPairs数据集以评估大语言模型在语义重叠摘要任务中的表现 large language model
28 MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT 提出MobiLlama以解决资源受限设备的语言模型需求 large language model ✅
29 Eight Methods to Evaluate Robust Unlearning in LLMs 提出八种方法评估大型语言模型的鲁棒性去学习 large language model
30 HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization 提出HumanEval-XL以解决多语言代码生成评估不足问题 large language model ✅
31 StructLM: Towards Building Generalist Models for Structured Knowledge Grounding 提出StructLM以解决结构化知识基础的模型能力不足问题 large language model
32 Rethinking Negative Instances for Generative Named Entity Recognition 提出负实例以增强生成式命名实体识别性能 large language model
33 ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors 提出ShieldLM以解决大语言模型安全检测问题 large language model ✅
34 Immunization against harmful fine-tuning attacks 提出免疫机制以应对有害微调攻击问题 large language model
35 Unraveling Babel: Exploring Multilingual Activation Patterns of LLMs and Their Applications 提出多语言激活模式分析方法以优化大语言模型 large language model
36 Unveiling the Truth and Facilitating Change: Towards Agent-based Large-scale Social Movement Simulation 提出HiSim框架以解决社交运动模拟中的效率与有效性问题 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🔗⭐
37 DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models 提出DenseSSM以提升状态空间模型在大语言模型中的效率 Mamba SSM state space model ✅
38 SKILL: Similarity-aware Knowledge distILLation for Speech Self-Supervised Learning 提出SKILL以提升语音自监督学习的蒸馏效率 distillation
39 Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings 提出多任务对比学习以提升8192-token双语文本嵌入性能 contrastive learning
40 LLM Inference Unveiled: Survey and Roofline Model Insights 提出屋顶线模型框架以优化大语言模型推理效率 distillation large language model

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
41 Where Do We Go from Here? Multi-scale Allocentric Relational Inference from Natural Spatial Descriptions 提出Rendezvous任务以解决自然语言空间描述中的导航问题 egocentric

⬅️ 返回 cs.CL 首页 · 🏠 返回主页