cs.CL（2023-12-22）

📊 共 14 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) (12 🔗1) 支柱一：机器人控制 (Robot Control) (1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 Moderating New Waves of Online Hate with Chain-of-Thought Reasoning in Large Language Models 提出HATEGUARD框架，利用思维链推理的大语言模型应对新型网络仇恨浪潮。 large language model chain-of-thought
2 Towards a Unified Multimodal Reasoning Framework 融合CoT推理与VQA技术，提升语言模型在多模态推理问答中的准确性 multimodal chain-of-thought
3 Robust Knowledge Extraction from Large Language Models using Social Choice Theory 利用社会选择理论，提升大语言模型知识提取的鲁棒性 large language model
4 Large Language Model (LLM) Bias Index -- LLMBI 提出LLMBI，用于量化和解决大型语言模型中存在的偏见问题。 large language model
5 MetaAID 2.5: A Secure Framework for Developing Metaverse Applications via Large Language Models MetaAID 2.5：一种基于大语言模型的元宇宙应用安全开发框架 large language model
6 Empowering Working Memory for Large Language Model Agents 提出基于工作记忆中心枢纽和情景缓冲区的LLM Agent架构，提升复杂推理能力 large language model
7 Personalized Large Language Model Assistant with Evolving Conditional Memory 提出一种具备演化条件记忆的个性化大语言模型助手框架 large language model
8 Aurora:Activating Chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-Tuning Aurora：通过指令微调激活Mixtral-8x7B稀疏专家混合模型的中文对话能力 large language model instruction following ✅
9 Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention 提出SparseCBM，利用稀疏性引导实现LLM的整体可解释性，并支持推理时干预。 large language model
10 Semantic Parsing for Complex Data Retrieval: Targeting Query Plans vs. SQL for No-Code Access to Relational Databases 提出QPL查询语言，简化复杂数据检索的语义解析，提升非程序员数据库访问能力。 large language model
11 Reasons to Reject? Aligning Language Models with Judgments 提出对比非似然训练(CUT)框架，利用语言反馈提升大语言模型对齐效果 large language model
12 Theory of Hallucinations based on Equivariance 提出基于等变性的幻觉理论，并设计实验评估语言模型的等变性学习能力 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
13 Don't Believe Everything You Read: Enhancing Summarization Interpretability through Automatic Identification of Hallucinations in Large Language Models 提出一种token级别幻觉识别方法，提升LLM在对话摘要任务中的可解释性和忠实度。 manipulation large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
14 YAYI 2: Multilingual Open-Source Large Language Models 提出YAYI 2：一个300亿参数的多语言开源大型语言模型，提升中文场景性能。 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页