cs.CL（2024-04-22）

📊 共 33 篇论文 | 🔗 11 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (32 🔗10) 支柱二：RL算法与架构 (RL & Architecture) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (32 篇)

#题目一句话要点标签🔗⭐
1 WangLab at MEDIQA-M3G 2024: Multimodal Medical Answer Generation using Large Language Models 提出多模态医疗问答生成方法以解决医学视觉问答挑战 large language model multimodal
2 PARAMANU-GANITA: Can Small Math Language Models Rival with Large Language Models on Mathematical Reasoning? 提出Paramanu-Ganita以解决小型数学语言模型的推理能力问题 large language model chain-of-thought ✅
3 Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension Training 提出VCAR以解决多模态数学推理中的视觉理解问题 large language model multimodal
4 SpaceByte: Towards Deleting Tokenization from Large Language Modeling 提出SpaceByte以解决大语言模型中的分词问题 large language model
5 A Survey on Self-Evolution of Large Language Models 提出自我进化框架以解决大语言模型的学习瓶颈问题 large language model ✅
6 Integrating Chemistry Knowledge in Large Language Models via Prompt Engineering 通过提示工程整合化学知识以提升大语言模型性能 large language model
7 A Survey on Efficient Inference for Large Language Models 提出高效推理方法以解决大语言模型的资源限制问题 large language model
8 Navigating the Path of Writing: Outline-guided Text Generation with Large Language Models 提出WritingPath框架以解决高质量文本生成问题 large language model
9 MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts 提出MixLoRA以解决大语言模型微调中的资源效率问题 large language model
10 Fine-Tuning Large Language Models to Translate: Will a Touch of Noisy Data in Misaligned Languages Suffice? 通过细调大语言模型实现翻译，探索噪声数据的影响 large language model
11 Information Re-Organization Improves Reasoning in Large Language Models 提出信息重组方法以提升大语言模型的推理能力 large language model ✅
12 A User-Centric Multi-Intent Benchmark for Evaluating Large Language Models 提出用户中心的多意图基准以评估大型语言模型 large language model ✅
13 MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making 提出MDAgents框架以优化医疗决策中的LLMs协作 large language model foundation model ✅
14 Tree of Reviews: A Tree-based Dynamic Iterative Retrieval Framework for Multi-hop Question Answering 提出Tree of Reviews框架以解决多跳问答中的检索问题 large language model chain-of-thought
15 VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models 提出VALOR-EVAL以解决大规模视觉语言模型的幻觉问题 large language model
16 OpenELM: An Efficient Language Model Family with Open Training and Inference Framework 提出OpenELM以提升大语言模型的可复现性与透明性 large language model ✅
17 RTP-LX: Can LLMs Evaluate Toxicity in Multilingual Scenarios? 提出RTP-LX以解决多语言环境下的有害内容检测问题 large language model
18 Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs 揭示大型语言模型中的通用监狱后门问题 large language model
19 SnapKV: LLM Knows What You are Looking for Before Generation 提出SnapKV以解决长输入序列KV缓存效率问题 large language model
20 Pixels and Predictions: Potential of GPT-4V in Meteorological Imagery Analysis and Forecast Communication 评估GPT-4V在气象图像分析中的应用潜力 large language model
21 Beyond Scaling: Predicting Patent Approval with Domain-specific Fine-grained Claim Dependency Graph 提出FLAN图以解决专利审批预测问题 large language model ✅
22 Performance Characterization of Expert Router for Scalable LLM Inference 提出Expert Router以解决大规模LLM推理的性能挑战 large language model
23 Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone 提出phi-3系列语言模型以实现手机端高效推理 multimodal
24 Benchmarking Advanced Text Anonymisation Methods: A Comparative Study on Novel and Traditional Approaches 比较传统与先进文本匿名化方法以提升数据隐私保护 large language model
25 Protecting Your LLMs with Information Bottleneck 提出信息瓶颈保护器以增强大语言模型安全性 large language model
26 FASTTRACK: Fast and Accurate Fact Tracing for LLMs 提出FASTTRACK以解决现有事实追踪方法的效率与准确性问题 large language model
27 Better Synthetic Data by Retrieving and Transforming Existing Datasets 提出DataTune以改善合成数据生成问题 large language model ✅
28 Automated Long Answer Grading with RiceChem Dataset 提出自动化长答案评分方法以解决教育领域评估挑战 large language model ✅
29 Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations 提出GARAG以解决RAG系统对低级扰动的脆弱性问题 large language model
30 MARIO Eval: Evaluate Your Math LLM with your Math LLM--A mathematical dataset evaluation toolkit 提出MARIO Eval以解决数学数据集评估不一致问题 large language model ✅
31 Context-Enhanced Language Models for Generating Multi-Paper Citations 提出基于大语言模型的多论文引用生成方法以解决引用文本构建问题 large language model
32 Understanding the role of FFNs in driving multilingual behaviour in LLMs 通过分析FFNs推动LLMs的多语言行为 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🔗⭐
33 Generating Attractive and Authentic Copywriting from Customer Reviews 提出基于客户评价生成吸引人的产品文案以解决内容单一问题 reinforcement learning large language model ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页