cs.CL（2023-10-08）

📊 共 28 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) (23 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (23 篇)

#题目一句话要点标签🔗⭐
1 MULTISCRIPT: Multimodal Script Learning for Supporting Open Domain Everyday Tasks 提出MultiScript以解决开放领域日常任务脚本生成问题 large language model multimodal
2 Self-Knowledge Guided Retrieval Augmentation for Large Language Models 提出自知识引导的检索增强方法以提升大语言模型性能 large language model chain-of-thought
3 Towards Better Chain-of-Thought Prompting Strategies: A Survey 系统总结链式思维提示策略以提升大语言模型性能 large language model chain-of-thought
4 Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models 提出FOLK推理以解决无标注数据的声明验证问题 large language model
5 Factuality Challenges in the Era of Large Language Models 探讨大型语言模型时代的事实性挑战及应对策略 large language model
6 ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Report Generation Based on Multi-institution and Multi-system Data 提出ChatRadio-Valuer以解决放射科报告生成的通用性挑战 large language model
7 MenatQA: A New Dataset for Testing the Temporal Comprehension and Reasoning Abilities of Large Language Models 提出MenatQA数据集以评估大语言模型的时间理解与推理能力 large language model
8 Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements 提出三种方法以提升大语言模型的同理心响应生成能力 large language model
9 Probing Large Language Models from A Human Behavioral Perspective 从人类行为视角探讨大型语言模型的预测机制 large language model
10 Do Large Language Models Know about Facts? 提出Pinocchio基准以评估大型语言模型的事实知识 large language model
11 Retrieval-Generation Synergy Augmented Large Language Models 提出迭代检索-生成协同框架以提升推理能力 large language model
12 Benchmarking Large Language Models with Augmented Instructions for Fine-grained Information Extraction 提出细粒度信息提取基准数据集以提升大语言模型性能 large language model
13 BRAINTEASER: Lateral Thinking Puzzles for Large Language Models 提出BRAINTEASER以解决语言模型的侧向思维能力不足问题 large language model
14 FakeGPT: Fake News Generation, Explanation and Detection of Large Language Models 提出FakeGPT以解决假新闻生成、解释与检测问题 large language model
15 Toolink: Linking Toolkit Creation and Using through Chain-of-Solving on Open-Source Model 提出Toolink框架以解决开放源模型工具使用的适应性问题 large language model chain-of-thought
16 Self-Convinced Prompting: Few-Shot Question Answering with Repeated Introspection 提出自我确认提示框架以提升少样本问答性能 large language model chain-of-thought
17 Are Emily and Greg Still More Employable than Lakisha and Jamal? Investigating Algorithmic Hiring Bias in the Era of ChatGPT 利用LLMs评估算法招聘中的偏见问题 large language model
18 Guideline Learning for In-context Information Extraction 提出指导学习框架以提升上下文信息提取性能 large language model
19 Distantly-Supervised Joint Extraction with Noise-Robust Learning 提出DENRL框架以解决远程监督下的联合实体关系提取问题 large language model
20 Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems 提出评估对话系统中的个性化偏见以降低社会风险 large language model
21 Scaling Laws of RoPE-based Extrapolation 提出RoPE扩展的缩放法则以提升LLM的外推能力 large language model
22 On the Zero-Shot Generalization of Machine-Generated Text Detectors 提出机器生成文本检测器的零-shot泛化方法 large language model
23 Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature 提出Fast-DetectGPT以解决机器生成文本检测效率低的问题 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
24 DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models 提出DialCoT以解决小型语言模型推理能力不足问题 PPO large language model chain-of-thought
25 Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback 提出产品专家模型以解决强化学习中的长度偏差问题 reinforcement learning large language model
26 Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classification 提出HJCL以解决层次化多标签文本分类中的对比学习问题 contrastive learning
27 Domain Knowledge Graph Construction Via A Simple Checker 提出基于简单检查器的知识图谱构建方法以解决半导体设计问题 distillation large language model

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

#题目一句话要点标签🔗⭐
28 Enhancing Argument Structure Extraction with Efficient Leverage of Contextual Information 提出ECASE模型以提高论证结构提取的上下文利用效率 ASE

⬅️ 返回 cs.CL 首页 · 🏠 返回主页