cs.CL（2024-09-14）

📊 共 14 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 ODE: Open-Set Evaluation of Hallucinations in Multimodal Large Language Models 提出ODE：一种开放集动态评估多模态大语言模型幻觉的方法 large language model multimodal
2 IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-Web 提出IW-Bench基准，评估大型多模态模型在图像到Web转换任务中的性能。 multimodal chain-of-thought
3 Generating Event-oriented Attribution for Movies via Two-Stage Prefix-Enhanced Multimodal LLM 提出双阶段前缀增强多模态LLM，用于生成电影事件导向的属性 large language model multimodal
4 Efficient Fine-Tuning of Large Language Models for Automated Medical Documentation MediGen：高效微调LLaMA3-8B，自动化生成医疗文档，减轻医生负担 large language model
5 Autoregressive + Chain of Thought = Recurrent: Recurrence's Role in Language Models' Computability and a Revisit of Recurrent Transformer 研究Transformer计算能力的局限性，并探讨CoT如何弥补循环计算的缺失。 chain-of-thought
6 ASR Error Correction using Large Language Models 利用大语言模型提升ASR纠错性能，无需访问底层代码或模型权重。 large language model
7 Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Models 对比检索增强与参数高效微调，实现大语言模型隐私保护的个性化 large language model
8 Uddessho: An Extensive Benchmark Dataset for Multimodal Author Intent Classification in Low-Resource Bangla Language 提出Uddessho数据集，用于低资源孟加拉语多模态作者意图分类。 multimodal
9 Enhancing LLM Problem Solving with REAP: Reflection, Explicit Problem Deconstruction, and Advanced Prompting REAP方法通过反思、分解和高级提示增强LLM的问题解决能力 large language model
10 Constructive Approach to Bidirectional Influence between Qualia Structure and Language Emergence 构建语言涌现与感受质结构双向影响模型，探索具身认知 multimodal
11 Thinking Before Speaking: A Role-playing Model with Mindset 提出基于思维模式的角色扮演模型，提升LLM的角色模拟真实度 large language model
12 Keeping Humans in the Loop: Human-Centered Automated Annotation with Generative AI 提出以人为本的框架，评估生成式AI在社交媒体文本自动标注中的应用，强调人工验证的重要性。 large language model
13 Measuring the Influence of Incorrect Code on Test Generation 研究代码正确性对LLM测试生成的影响：正确代码提升测试准确率57% large language model
14 NovAScore: A New Automated Metric for Evaluating Document Level Novelty 提出NovAScore，一种自动化的文档级新颖性评估指标。 large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页