cs.CL（2024-08-02）

📊 共 23 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) (23 🔗4)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (23 篇)

#题目一句话要点标签🔗⭐
1 Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs ICCA框架评估多模态LLM在对话中自发提升沟通效率的能力 large language model multimodal ✅
2 MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models 提出MuChoMusic基准，用于评估多模态音频-语言模型在音乐理解方面的能力 multimodal
3 The Impact of Hyperparameters on Large Language Model Inference Performance: An Evaluation of vLLM and HuggingFace Pipelines 研究超参数对大语言模型推理性能的影响，对比vLLM和HuggingFace Pipelines。 large language model
4 Fairness in Large Language Models in Three Hours 系统性探讨大语言模型中的公平性问题及解决方案 large language model ✅
5 High-Throughput Phenotyping of Clinical Text Using Large Language Models 利用大型语言模型实现临床文本的高通量表型分析自动化 large language model
6 Coalitions of Large Language Models Increase the Robustness of AI Agents 提出基于大语言模型联盟的AI Agent，提升鲁棒性并降低运营成本 large language model
7 The Mismeasure of Man and Models: Evaluating Allocational Harms in Large Language Models 提出RABBI指标，评估大语言模型在资源分配决策中的潜在偏差危害。 large language model
8 Leveraging Encoder-only Large Language Models for Mobile App Review Feature Extraction 利用Encoder-only大语言模型提升移动应用评论特征抽取性能 large language model
9 Prompt Recursive Search: A Living Framework with Adaptive Growth in LLM Auto-Prompting 提出Prompt递归搜索框架，自适应调整LLM提示策略，提升复杂问题求解能力。 large language model chain-of-thought
10 Evaluating the Impact of Advanced LLM Techniques on AI-Lecture Tutors for a Robotics Course 评估LLM技术在机器人课程AI辅导中的应用效果 large language model
11 Toward Automatic Relevance Judgment using Vision--Language Models for Image--Text Retrieval Evaluation 利用视觉-语言模型提升图像-文本检索的相关性判断 large language model
12 Deep Learning based Visually Rich Document Content Understanding: A Survey 综述：基于深度学习的富视觉文档内容理解方法 multimodal
13 Misinforming LLMs: vulnerabilities, challenges and opportunities 揭示大型语言模型脆弱性：信息误导漏洞、挑战与机遇 large language model
14 PERSOMA: PERsonalized SOft ProMpt Adapter Architecture for Personalized Language Prompting PERSOMA：个性化软提示适配器架构，有效捕捉用户历史交互信息，提升个性化语言提示效果。 large language model
15 MoDE: Effective Multi-task Parameter Efficient Fine-Tuning with a Mixture of Dyadic Experts MoDE：一种基于混合Dyadic专家的高效多任务参数高效微调方法 large language model
16 Prompt Refinement or Fine-tuning? Best Practices for using LLMs in Computational Social Science Tasks 针对计算社会科学任务，研究LLM微调与提示工程的最佳实践 large language model
17 FANNO: Augmenting High-Quality Instruction Data with Open-Sourced LLMs Only FANNO：仅用开源LLM增强高质量指令数据，无需人工标注或昂贵API。 large language model
18 RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework RAGEval：提出场景特定的RAG评估数据集生成框架，解决RAG系统在特定场景下评估难题。 large language model ✅
19 CFBench: A Comprehensive Constraints-Following Benchmark for LLMs 提出CFBench，一个全面的约束遵循基准，用于评估大型语言模型。 large language model ✅
20 Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer 提出任务提示向量，通过多任务软提示迁移实现高效初始化。 large language model
21 IAI Group at CheckThat! 2024: Transformer Models and Data Augmentation for Checkworthy Claim Detection IAI团队在CheckThat! 2024中利用Transformer模型和数据增强进行可信声明检测 chain-of-thought
22 Bridging Information Gaps in Dialogues With Grounded Exchanges Using Knowledge Graphs 提出BridgeKG数据集，利用大语言模型弥合对话系统中知识图谱的信息鸿沟 large language model
23 Automatic Extraction of Relationships among Motivations, Emotions and Actions from Natural Language Texts 提出一种基于图的框架，利用自然语言文本自动提取动机、情感和行为之间的关系。 large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页