cs.CL（2024-09-11）

📊 共 17 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) (13 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗⭐
1 Leveraging Unstructured Text Data for Federated Instruction Tuning of Large Language Models 提出FedIT-U2S框架，利用非结构化文本数据进行联邦指令调优，扩展LLM应用场景。 large language model
2 Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model 提出WikiOFGraph：利用大语言模型合成通用领域知识图谱到文本生成数据集，提升图文一致性。 large language model
3 Context-Aware Membership Inference Attacks against Pre-trained Large Language Models 提出上下文感知成员推理攻击，针对预训练大语言模型的隐私风险 large language model
4 A Simplified Retriever to Improve Accuracy of Phenotype Normalizations by Large Language Models 提出一种简化的检索器，通过大语言模型提升表型标准化的准确性 large language model
5 Recent Trends of Multimodal Affective Computing: A Survey from NLP Perspective 综述：NLP视角下的多模态情感计算最新趋势研究 multimodal
6 Contextualization of ASR with LLM using phonetic retrieval-based augmentation 提出基于音素检索增强的LLM语音识别上下文方法，提升命名实体识别准确率 large language model multimodal
7 Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem 提出Cross-Refine框架，通过生成器-评论家协同学习提升自然语言解释生成质量。 large language model
8 Understanding Knowledge Drift in LLMs through Misinformation 研究LLM在虚假信息下的知识漂移现象，揭示其脆弱性并评估不确定性。 large language model ✅
9 Native vs Non-Native Language Prompting: A Comparative Analysis 对比原生与非原生语言Prompt，探究其在阿拉伯语NLP任务中的性能差异 large language model
10 You Have Thirteen Hours in Which to Solve the Labyrinth: Enhancing AI Game Masters with Function Calling 利用函数调用增强AI游戏大师，提升叙事质量与状态一致性 large language model
11 SimulBench: Evaluating Language Models with Creative Simulation Tasks SimulBench：提出创造性模拟任务评测基准，评估LLM在Linux终端和文本游戏等场景下的能力 large language model
12 MOSAIC: Multiple Observers Spotting AI Content 提出MOSAIC，通过集成多个观测器LLM来更鲁棒地检测AI生成内容。 large language model ✅
13 Think Together and Work Better: Combining Humans' and LLMs' Think-Aloud Outcomes for Effective Text Evaluation 提出InteractEval框架以提升文本评估效果 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
14 Beyond IID: Optimizing Instruction Learning from the Perspective of Instruction Interaction and Dependency 针对指令交互与依赖，优化指令学习以提升大语言模型性能 curriculum learning large language model
15 Learning Efficient Recursive Numeral Systems via Reinforcement Learning 提出基于强化学习的递归数字系统学习方法，实现高效通信 reinforcement learning

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

#题目一句话要点标签🔗⭐
16 Propaganda to Hate: A Multimodal Analysis of Arabic Memes with Multi-Agent LLMs 提出基于多智能体LLM的框架，分析阿拉伯语Meme中的仇恨宣传内容 HuMoR multimodal ✅

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
17 Salmon: A Suite for Acoustic Language Model Evaluation 提出SALMon：用于评估声学语言模型的新型评测套件 PULSE

⬅️ 返回 cs.CL 首页 · 🏠 返回主页