cs.CL（2023-11-09）

📊 共 17 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14 🔗3) 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)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 Long-Horizon Dialogue Understanding for Role Identification in the Game of Avalon with Large Language Models 提出长时间对话理解方法以识别阿瓦隆游戏中的角色 large language model multimodal ✅
2 Large Language Models can Strategically Deceive their Users when Put Under Pressure 揭示大型语言模型在压力下的战略性欺骗行为 large language model
3 Challenging the Validity of Personality Tests for Large Language Models 挑战大型语言模型人格测试的有效性 large language model
4 A Survey of Large Language Models in Medicine: Progress, Application, and Challenge 综述大型语言模型在医学中的应用与挑战 large language model ✅
5 Characterizing Large Language Models as Rationalizers of Knowledge-intensive Tasks 提出知识引导的合理化生成方法以提升LLM的可信度 large language model
6 BeLLM: Backward Dependency Enhanced Large Language Model for Sentence Embeddings 提出BeLLM以增强句子嵌入的语义相似性测量 large language model
7 A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions 提出对大型语言模型幻觉现象的全面调查与分类 large language model
8 Large Language Models and Prompt Engineering for Biomedical Query Focused Multi-Document Summarisation 利用提示工程和GPT-3.5实现生物医学多文档摘要 large language model
9 Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization 通过W4A8量化提升大语言模型计算效率 large language model
10 Efficiently Adapting Pretrained Language Models To New Languages 提出高效适应预训练语言模型以解决低资源语言问题 large language model
11 Prompt Engineering a Prompt Engineer 提出PE2方法以优化大语言模型的提示工程 large language model
12 Deep Natural Language Feature Learning for Interpretable Prediction 提出自然语言特征学习方法以实现可解释预测 large language model
13 Cognitively Inspired Components for Social Conversational Agents 提出认知启发组件以解决社交对话代理的技术与社会问题 large language model
14 Conic10K: A Challenging Math Problem Understanding and Reasoning Dataset 提出Conic10K数据集以解决数学问题理解与推理挑战 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🔗⭐
15 Removing RLHF Protections in GPT-4 via Fine-Tuning 提出通过微调去除GPT-4的RLHF保护机制 reinforcement learning RLHF large language model
16 Text Representation Distillation via Information Bottleneck Principle 提出基于信息瓶颈原理的知识蒸馏方法以提升文本表示模型性能 distillation

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

#题目一句话要点标签🔗⭐
17 PRODIGy: a PROfile-based DIalogue Generation dataset 提出基于个人档案的对话生成数据集以提升对话一致性 implicit representation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页