cs.CL（2024-11-26）

📊 共 16 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) (13 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3)

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

#题目一句话要点标签🔗⭐
1 How do Multimodal Foundation Models Encode Text and Speech? An Analysis of Cross-Lingual and Cross-Modal Representations 分析多模态模型如何编码文本与语音，揭示跨语言和跨模态表征差异 foundation model multimodal
2 Leveraging Large Language Models and Topic Modeling for Toxicity Classification 利用大型语言模型和主题建模改进毒性分类，提升模型公平性。 large language model ✅
3 What Differentiates Educational Literature? A Multimodal Fusion Approach of Transformers and Computational Linguistics 提出Transformer与计算语言学融合的多模态方法，用于评估教育文本难度并辅助课程适配。 multimodal
4 Strategic Prompting for Conversational Tasks: A Comparative Analysis of Large Language Models Across Diverse Conversational Tasks 对比分析大型语言模型在不同对话任务中的策略性提示效果 large language model
5 One Mind, Many Tongues: A Deep Dive into Language-Agnostic Knowledge Neurons in Large Language Models 提出MATRICE方法，解决大语言模型中语言无关知识神经元定位不确定性问题。 large language model
6 Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey 综述：基于多模态大语言模型在视觉问答中的自然语言理解与推理 large language model multimodal
7 Star Attention: Efficient LLM Inference over Long Sequences 提出Star Attention，通过块稀疏注意力加速长序列LLM推理。 large language model
8 Different Bias Under Different Criteria: Assessing Bias in LLMs with a Fact-Based Approach 提出基于事实的LLM偏见评估指标，揭示不同标准下的偏见差异 large language model
9 Meaningless is better: hashing bias-inducing words in LLM prompts improves performance in logical reasoning and statistical learning 提出一种基于哈希的提示方法，提升LLM在逻辑推理和统计学习中的性能 large language model
10 Socio-Emotional Response Generation: A Human Evaluation Protocol for LLM-Based Conversational Systems 提出一种基于社会情感策略规划的对话系统，提升LLM生成回复的质量和可控性。 large language model
11 Overcoming Non-monotonicity in Transducer-based Streaming Generation 提出MonoAttn-Transducer，解决Transducer在非单调对齐流式生成任务中的问题。 TAMP
12 Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats 自适应部署不可信LLM以降低分布式威胁 large language model
13 Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning TIPA：通过学习Token内部结构提升LLM的字符级理解能力 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
14 Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach 提出一种无判别器的多模态大语言模型自提升方法，提升效率与鲁棒性 preference learning large language model multimodal
15 Safe to Serve: Aligning Instruction-Tuned Models for Safety and Helpfulness 通过安全指令调优对齐语言模型，提升安全性和实用性 DPO direct preference optimization large language model
16 Systematic Reward Gap Optimization for Mitigating VLM Hallucinations 提出主题级偏好重写(TPR)框架，系统优化奖励差距以缓解VLM幻觉问题 DPO direct preference optimization

⬅️ 返回 cs.CL 首页 · 🏠 返回主页