cs.CL（2024-07-31）

📊 共 17 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (16 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#题目一句话要点标签🔗⭐
1 Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models 提出CIDER，利用跨模态信息检测多模态大语言模型中的越狱攻击。 large language model multimodal
2 Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment 提出负注意力得分对齐(NASA)方法，解决大语言模型在二元决策任务中的负偏差问题 large language model
3 Improving Faithfulness of Large Language Models in Summarization via Sliding Generation and Self-Consistency 提出SliSum方法，通过滑动生成和自洽性提升大型语言模型在摘要生成中的忠实度 large language model
4 Tracing Intricate Cues in Dialogue: Joint Graph Structure and Sentiment Dynamics for Multimodal Emotion Recognition 提出GraphSmile模型，通过图结构和情感动态建模提升多模态情感识别效果 multimodal
5 Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models 提出ReSet方法，在指令跟随和忠实性之间实现语言模型性能提升 instruction following
6 Towards interfacing large language models with ASR systems using confidence measures and prompting 提出基于置信度过滤和提示的大语言模型ASR转录后处理方法 large language model
7 Performance of Recent Large Language Models for a Low-Resourced Language 评估大型语言模型在低资源语言锡兰语上的性能，并探索微调潜力。 large language model
8 Beyond Silent Letters: Amplifying LLMs in Emotion Recognition with Vocal Nuances 提出SpeechCueLLM，利用语音特征描述增强LLM在情感识别中的表现 large language model multimodal
9 Automatic Generation of Behavioral Test Cases For Natural Language Processing Using Clustering and Prompting 提出一种基于聚类和提示的NLP行为测试用例自动生成方法 large language model
10 Synth-Empathy: Towards High-Quality Synthetic Empathy Data 提出Synth-Empathy，一种基于LLM的高质量合成共情数据生成与选择流程 large language model
11 Distributed In-Context Learning under Non-IID Among Clients 提出一种分布式非独立同分布场景下的上下文学习预算分配方法 large language model
12 PMoE: Progressive Mixture of Experts with Asymmetric Transformer for Continual Learning 提出PMoE，利用非对称Transformer和渐进式专家混合模型解决LLM的持续学习难题。 large language model
13 Adaptive Retrieval-Augmented Generation for Conversational Systems 提出RAGate门控模型，自适应地决定对话系统是否需要检索增强生成。 large language model
14 Can LLMs "Reason" in Music? An Evaluation of LLMs' Capability of Music Understanding and Generation 评估LLM在音乐理解与生成中的推理能力，揭示其在多步音乐推理上的局限性 large language model
15 Generative Expressive Conversational Speech Synthesis 提出GPT-Talker，用于生成具有表现力的对话语音合成，并构建大规模自然对话语音数据集NCSSD。 multimodal ✅
16 QuestGen: Effectiveness of Question Generation Methods for Fact-Checking Applications QuestGen：利用问题生成方法提升事实核查应用效果 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
17 Model Attribution in LLM-Generated Disinformation: A Domain Generalization Approach with Supervised Contrastive Learning 提出基于监督对比学习的领域泛化方法，用于LLM生成虚假信息的模型溯源。 contrastive learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页