cs.CL（2024-03-04）

📊 共 30 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (27 🔗3) 支柱一：机器人控制 (Robot Control) (2 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (27 篇)

#题目一句话要点标签🔗⭐
1 An Improved Traditional Chinese Evaluation Suite for Foundation Model 提出TMMLU+以解决传统中文理解基准不足问题 large language model foundation model
2 Differentially Private Synthetic Data via Foundation Model APIs 2: Text 提出Aug-PE算法以解决文本数据的差分隐私合成问题 large language model foundation model ✅
3 Large Language Models in Fire Engineering: An Examination of Technical Questions Against Domain Knowledge 比较ChatGPT与Bard在消防工程中的应用效果 large language model
4 TopicDiff: A Topic-enriched Diffusion Approach for Multimodal Conversational Emotion Detection 提出TopicDiff以解决多模态对话情感检测中的主题信息不足问题 multimodal
5 SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models 提出SPUQ方法以解决大语言模型的不确定性量化问题 large language model
6 Leveraging Weakly Annotated Data for Hate Speech Detection in Code-Mixed Hinglish: A Feasibility-Driven Transfer Learning Approach with Large Language Models 提出利用弱标注数据的仇恨言论检测方法以解决Hinglish混合语言问题 large language model
7 Online Training of Large Language Models: Learn while chatting 提出在线训练大语言模型以解决用户个性化需求问题 large language model
8 PHAnToM: Persona-based Prompting Has An Effect on Theory-of-Mind Reasoning in Large Language Models 提出基于角色扮演的提示以改善大语言模型的心智理论推理能力 large language model
9 Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models 提出MPIKGC框架以提升知识图谱补全效果 large language model
10 Analyzing and Adapting Large Language Models for Few-Shot Multilingual NLU: Are We There Yet? 系统比较三种少样本多语言NLU方法以优化资源使用 large language model
11 Inference Acceleration for Large Language Models on CPUs 提出基于CPU的推理加速方法以提升大语言模型性能 large language model
12 Derivative-Free Optimization for Low-Rank Adaptation in Large Language Models 提出无导数优化方法以提升大语言模型的低秩适应性能 large language model
13 Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models 提出随机遮蔽部分推理步骤以提升语言模型的数学推理能力 large language model chain-of-thought
14 Rethinking LLM Language Adaptation: A Case Study on Chinese Mixtral 提出Chinese-Mixtral以提升中文理解与生成能力 large language model foundation model ✅
15 SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis 提出SciAssess以解决LLM在科学文献分析中的评估不足问题 large language model multimodal ✅
16 AS-ES Learning: Towards Efficient CoT Learning in Small Models 提出AS-ES学习以提高小模型的CoT学习效率 large language model chain-of-thought
17 Not All Layers of LLMs Are Necessary During Inference 提出AdaInfer以降低大语言模型推理成本 large language model
18 Breaking the Language Barrier: Can Direct Inference Outperform Pre-Translation in Multilingual LLM Applications? 提出直接推理方法以挑战多语言LLM中的预翻译问题 large language model
19 LLM vs. Lawyers: Identifying a Subset of Summary Judgments in a Large UK Case Law Dataset 提出基于大语言模型的方法以高效识别英国案例法中的摘要判决 large language model
20 Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning 提出关键点驱动的数据合成方法以提升数学推理能力 large language model
21 DECIDER: A Dual-System Rule-Controllable Decoding Framework for Language Generation 提出DECIDER框架以实现更人性化的语言生成控制 large language model
22 Birbal: An efficient 7B instruct-model fine-tuned with curated datasets 提出Birbal以解决大规模语言模型训练效率问题 foundation model
23 Using LLMs for the Extraction and Normalization of Product Attribute Values 利用大型语言模型提取和规范化产品属性值 large language model
24 Automated Generation of Multiple-Choice Cloze Questions for Assessing English Vocabulary Using GPT-turbo 3.5 提出基于GPT-turbo 3.5的自动生成多项选择填空题方法 large language model
25 LLM-Oriented Retrieval Tuner 提出LLM导向检索调优器以解决LLM与检索任务整合问题 large language model
26 Fostering the Ecosystem of Open Neural Encoders for Portuguese with Albertina PT* Family 提出开放神经编码器以增强葡萄牙语语言模型生态系统 large language model
27 WebCiteS: Attributed Query-Focused Summarization on Chinese Web Search Results with Citations 提出WebCiteS以解决中文网页搜索结果的引用聚焦摘要问题 large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
28 Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents 提出探索基础的轨迹优化方法以提升LLM代理性能 trajectory optimization DPO contrastive learning
29 FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMs 提出FKA-Owl以解决多模态假新闻检测问题 manipulation multimodal ✅

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

#题目一句话要点标签🔗⭐
30 Balancing Enhancement, Harmlessness, and General Capabilities: Enhancing Conversational LLMs with Direct RLHF 提出直接RLHF方法以解决对话LLM知识减少问题 reinforcement learning RLHF large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页