cs.CL（2024-01-31）

📊 共 27 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (24 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (24 篇)

#题目一句话要点标签🔗⭐
1 LongAlign: A Recipe for Long Context Alignment of Large Language Models 提出LongAlign以解决长上下文对齐问题 large language model instruction following ✅
2 Enhancing Large Language Model with Decomposed Reasoning for Emotion Cause Pair Extraction 提出DECC框架以解决情感原因对提取问题 large language model chain-of-thought
3 Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoning 提出演绎束搜索以解决链式推理中的错误累积问题 large language model chain-of-thought
4 Assertion Detection Large Language Model In-context Learning LoRA Fine-tuning 提出基于大语言模型的断言检测方法以解决临床文本分析问题 large language model chain-of-thought
5 An Early Categorization of Prompt Injection Attacks on Large Language Models 提出对大语言模型的提示注入攻击分类以应对安全挑战 large language model
6 SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering 提出SWEA框架以高效更新大语言模型的事实知识 large language model
7 Contextual Feature Extraction Hierarchies Converge in Large Language Models and the Brain 探讨大型语言模型与人脑语言处理的相似性 large language model
8 Navigating the OverKill in Large Language Models 提出Self-Contrastive Decoding以解决大语言模型过度拒绝问题 large language model
9 Large Language Models for Mathematical Reasoning: Progresses and Challenges 综述大型语言模型在数学推理中的进展与挑战 large language model
10 I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBench 提出AwareBench基准以评估大型语言模型的意识能力 large language model ✅
11 Neighboring Perturbations of Knowledge Editing on Large Language Models 提出PEAK框架以解决大语言模型知识编辑中的邻近扰动问题 large language model ✅
12 LLM Voting: Human Choices and AI Collective Decision Making 研究LLM投票行为以提升人机决策一致性 large language model chain-of-thought
13 Emergency Department Decision Support using Clinical Pseudo-notes 提出多嵌入模型MEME以优化急诊科决策支持 foundation model multimodal
14 Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners? 研究语言模型在解题中是否表现出与人类相同的认知偏差 large language model
15 Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks 提出ReCoE基准以解决知识编辑中的推理传播问题 chain-of-thought
16 Large Scale Generative AI Text Applied to Sports and Music 提出生成式AI文本以解决大型体育和音乐事件内容生产问题 multimodal
17 Paramanu: Compact and Competitive Monolingual Language Models for Low-Resource Morphologically Rich Indian Languages 提出PARAMANU以解决低资源印度语言模型构建问题 large language model ✅
18 Evaluating the Capabilities of LLMs for Supporting Anticipatory Impact Assessment 利用LLMs支持前瞻性影响评估的能力评估 large language model
19 Global-Liar: Factuality of LLMs over Time and Geographic Regions 提出Global-Liar数据集以评估LLMs的事实性与偏见问题 large language model
20 LLMs Simulate Big Five Personality Traits: Further Evidence 研究大型语言模型模拟五大人格特质的能力 large language model
21 Employing Label Models on ChatGPT Answers Improves Legal Text Entailment Performance 利用标签模型提升ChatGPT在法律文本蕴涵任务中的表现 large language model
22 Probing Language Models' Gesture Understanding for Enhanced Human-AI Interaction 探讨语言模型的手势理解以增强人机交互 large language model
23 WSC+: Enhancing The Winograd Schema Challenge Using Tree-of-Experts 提出Tree-of-Experts方法以增强Winograd Schema Challenge large language model
24 SPECTRUM: Speaker-Enhanced Pre-Training for Long Dialogue Summarization 提出说话者增强预训练方法以解决长对话摘要问题 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🔗⭐
25 Enhancing End-to-End Multi-Task Dialogue Systems: A Study on Intrinsic Motivation Reinforcement Learning Algorithms for Improved Training and Adaptability 提出内在动机强化学习算法以提升多任务对话系统的训练与适应性 reinforcement learning PPO distillation
26 Scavenging Hyena: Distilling Transformers into Long Convolution Models 提出知识蒸馏方法以提高长卷积模型的效率 distillation large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
27 Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data 提出基准测试以评估VLM在地球观测数据上的表现 scene understanding ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页