cs.CL（2024-02-25）

📊 共 16 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) (13 🔗5) 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 LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting 提出LSTPrompt以解决时间序列预测中的提示方法不足问题 large language model chain-of-thought
2 Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing 提出SEMANTICSMOOTH以解决大语言模型的监狱破解攻击问题 large language model instruction following ✅
3 InstructEdit: Instruction-based Knowledge Editing for Large Language Models 提出InstructEdit以解决多任务知识编辑的通用性问题 large language model ✅
4 From Text to Transformation: A Comprehensive Review of Large Language Models' Versatility 系统评估大型语言模型在多领域的应用潜力 large language model
5 UrbanGPT: Spatio-Temporal Large Language Models 提出UrbanGPT以解决城市环境时空预测问题 large language model
6 Likelihood-based Mitigation of Evaluation Bias in Large Language Models 提出基于似然性的评估偏差缓解方法以优化大语言模型 large language model
7 How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study 通过层级探测研究揭示大语言模型的上下文知识编码能力 large language model ✅
8 Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression 提出Gist-COCO以解决长提示输入成本高的问题 large language model chain-of-thought ✅
9 Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy 提出多种群体感知优化方法以解决机器生成文本检测问题 large language model ✅
10 Evaluating Robustness of Generative Search Engine on Adversarial Factual Questions 评估生成搜索引擎在对抗性事实问题上的鲁棒性 large language model
11 LoRA Meets Dropout under a Unified Framework 提出HiddenKey以解决LoRA与Dropout结合的过拟合问题 large language model
12 PeriodicLoRA: Breaking the Low-Rank Bottleneck in LoRA Optimization 提出PeriodicLoRA以突破LoRA优化中的低秩瓶颈 large language model
13 ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings 提出ASETF以解决大语言模型的安全防御问题 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 GraphWiz: An Instruction-Following Language Model for Graph Problems 提出GraphWiz以解决复杂图问题 DPO direct preference optimization large language model
15 How Likely Do LLMs with CoT Mimic Human Reasoning? 通过因果分析揭示LLMs推理过程中的偏差与改进方向 reinforcement learning large language model chain-of-thought
16 Don't Forget Your Reward Values: Language Model Alignment via Value-based Calibration 提出基于价值的校准方法以解决语言模型对人类偏好的对齐问题 reinforcement learning PPO RLHF

⬅️ 返回 cs.CL 首页 · 🏠 返回主页