cs.CL（2024-11-27）

📊 共 22 篇论文 | 🔗 2 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) (5 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱八：物理动画 (Physics-based Animation) (1) 支柱六：视频提取与匹配 (Video Extraction) (1)

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

#题目一句话要点标签🔗⭐
1 Can LLMs assist with Ambiguity? A Quantitative Evaluation of various Large Language Models on Word Sense Disambiguation 提出结合提示增强和知识库的LLM方法，提升词义消歧性能 large language model chain-of-thought
2 On the Effectiveness of Incremental Training of Large Language Models 研究表明，LLM增量分层训练在计算效率上不如传统全量训练。 large language model
3 Fine-Tuning Large Language Models for Scientific Text Classification: A Comparative Study 微调大型语言模型用于科学文本分类：一项对比研究 large language model
4 Retrofitting Large Language Models with Dynamic Tokenization 提出动态Token化方法，提升大语言模型在多语言场景下的效率与公平性。 large language model
5 Neutralizing Backdoors through Information Conflicts for Large Language Models 提出基于信息冲突的大语言模型后门防御方法，有效消除恶意行为。 large language model
6 Can bidirectional encoder become the ultimate winner for downstream applications of foundation models? 探讨双向编码器在下游任务中作为基础模型最优选择的潜力 foundation model
7 Automated Literature Review Using NLP Techniques and LLM-Based Retrieval-Augmented Generation 提出基于NLP技术和LLM的RAG方法，实现文献综述的自动生成。 large language model
8 Challenges in Adapting Multilingual LLMs to Low-Resource Languages using LoRA PEFT Tuning LoRA PEFT微调在低资源语言多语言LLM上的挑战与分析 large language model
9 New Faithfulness-Centric Interpretability Paradigms for Natural Language Processing 提出以忠实度为中心的可解释性范式，提升NLP模型解释的可靠性 large language model
10 Is my Meeting Summary Good? Estimating Quality with a Multi-LLM Evaluator 提出MESA：一种基于多LLM评估器的会议总结质量评估框架 large language model
11 ChatGPT as speechwriter for the French presidents 分析ChatGPT生成的法语总统演讲稿风格，揭示其与真实演讲的差异 large language model
12 GPT as ghostwriter at the White House 分析ChatGPT生成文本与美国总统演讲风格差异，揭示LLM在政治写作中的局限性 large language model
13 Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS 提出HiAR-ICL以解决复杂推理任务中的示例依赖问题 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
14 JPPO: Joint Power and Prompt Optimization for Accelerated Large Language Model Services 提出JPPO框架以解决大语言模型服务中的资源优化问题 reinforcement learning deep reinforcement learning large language model
15 Thai Financial Domain Adaptation of THaLLE -- Technical Report 针对泰国金融领域，提出THaLLE模型，解决领域知识不足问题。 DPO direct preference optimization large language model
16 Isolating authorship from content with semantic embeddings and contrastive learning 提出基于语义嵌入和对比学习的解耦方法，提升作者身份识别精度。 contrastive learning
17 Training and Evaluating Language Models with Template-based Data Generation 提出基于模板的数据生成方法TDG，用于训练和评估语言模型的数学推理能力。 reinforcement learning large language model ✅
18 Curriculum Demonstration Selection for In-Context Learning 提出课程演示选择方法以提升大语言模型的学习能力 curriculum learning large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
19 Emergence of Self-Identity in AI: A Mathematical Framework and Empirical Study with Generative Large Language Models 提出数学框架以量化人工智能中的自我身份问题 humanoid humanoid robot large language model
20 Hidden Data Privacy Breaches in Federated Learning 提出一种隐蔽的联邦学习数据重建攻击，可高效窃取高分辨率隐私数据。 manipulation

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

#题目一句话要点标签🔗⭐
21 AMPS: ASR with Multimodal Paraphrase Supervision AMPS：利用多模态复述监督提升多语言会话语音识别性能 AMP multimodal

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

#题目一句话要点标签🔗⭐
22 SentiXRL: An advanced large language Model Framework for Multilingual Fine-Grained Emotion Classification in Complex Text Environment 提出SentiXRL框架，用于多语言复杂文本环境中细粒度情感分类 motion retrieval large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页