cs.CL（2024-01-30）

📊 共 26 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) (23 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1)

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

#题目一句话要点标签🔗⭐
1 Incoherent Probability Judgments in Large Language Models 探讨大语言模型概率判断的不一致性及其原因 large language model
2 TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese 提出TeenyTinyLlama以解决巴西葡萄牙语低资源模型问题 large language model foundation model ✅
3 Weaver: Foundation Models for Creative Writing 提出Weaver以提升创意写作能力 large language model foundation model
4 Conditional and Modal Reasoning in Large Language Models 探讨大型语言模型在条件与模态推理中的局限性 large language model chain-of-thought
5 PACE: A Pragmatic Agent for Enhancing Communication Efficiency Using Large Language Models 提出PACE框架以提升大语言模型下的通信效率 large language model chain-of-thought
6 Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models 综述多模态大模型在仇恨言论审查中的应用与挑战 large language model multimodal
7 Rethinking Interpretability in the Era of Large Language Models 重新思考大语言模型时代的可解释性问题 large language model
8 Engineering A Large Language Model From Scratch 提出Atinuke模型以优化自然语言处理任务 large language model
9 Two Heads Are Better Than One: Integrating Knowledge from Knowledge Graphs and Large Language Models for Entity Alignment 提出LLMEA框架以解决知识图谱实体对齐问题 large language model
10 Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate 提出ScaleEval框架以解决LLMs评估可靠性问题 large language model ✅
11 Security and Privacy Challenges of Large Language Models: A Survey 综述大型语言模型的安全与隐私挑战及防护机制 large language model
12 Weak-to-Strong Jailbreaking on Large Language Models 提出弱到强的越狱攻击以解决大型语言模型的安全问题 large language model ✅
13 CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models 构建CRUD-RAG基准以提升检索增强生成模型评估 large language model
14 MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models 提出MT-Eval以解决多轮对话能力评估问题 large language model
15 Prospects for inconsistency detection using large language models and sheaves 利用大语言模型与层论检测逻辑不一致性 large language model
16 Performance Assessment of ChatGPT vs Bard in Detecting Alzheimer's Dementia 评估ChatGPT与Bard在阿尔茨海默病检测中的表现 large language model chain-of-thought
17 Efficient Tool Use with Chain-of-Abstraction Reasoning 提出链式抽象推理方法以提升多步推理中的工具使用效率 large language model chain-of-thought
18 Detecting mental disorder on social media: a ChatGPT-augmented explainable approach 提出基于ChatGPT的可解释抑郁症检测方法 large language model
19 Customizing Language Model Responses with Contrastive In-Context Learning 提出对比学习方法以优化语言模型响应 large language model
20 Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens 提出Infini-gram以提升n-gram语言模型的性能与应用 large language model
21 Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios 提出UltraTool以解决LLMs工具利用评估不足问题 large language model ✅
22 SemScore: Automated Evaluation of Instruction-Tuned LLMs based on Semantic Textual Similarity 提出SemScore以解决LLMs评估效率低下问题 large language model
23 Taking Action Towards Graceful Interaction: The Effects of Performing Actions on Modelling Policies for Instruction Clarification Requests 探讨动作执行对指令澄清请求建模政策的影响 instruction following

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
24 LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation 提出LLaMP框架以解决大语言模型在材料科学中的偏差问题 distillation large language model multimodal ✅
25 H2O-Danube-1.8B Technical Report 提出H2O-Danube系列语言模型以提升LLM性能 direct preference optimization large language model
26 Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive Learning 构建多元道德句子嵌入空间以解决道德判断二元化问题 contrastive learning

⬅️ 返回 cs.CL 首页 · 🏠 返回主页