cs.CL（2024-04-30）

📊 共 22 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) (17 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (17 篇)

#题目一句话要点标签🔗⭐
1 General Purpose Verification for Chain of Thought Prompting 提出通用验证方法以提升链式思维提示的推理能力 large language model chain-of-thought
2 SPAFIT: Stratified Progressive Adaptation Fine-tuning for Pre-trained Large Language Models 提出SPAFIT以解决大语言模型微调效率低下问题 large language model
3 Can Large Language Models put 2 and 2 together? Probing for Entailed Arithmetical Relationships 探讨大型语言模型在算术推理中的局限性 large language model
4 Large Language Model Agent for Fake News Detection 提出FactAgent以解决假新闻检测中的效率问题 large language model
5 Towards a Search Engine for Machines: Unified Ranking for Multiple Retrieval-Augmented Large Language Models 提出uRAG框架以统一检索增强生成系统的排名 large language model
6 Better & Faster Large Language Models via Multi-token Prediction 通过多标记预测提升大型语言模型的效率与性能 large language model
7 Automated Generation of High-Quality Medical Simulation Scenarios Through Integration of Semi-Structured Data and Large Language Models 提出基于半结构化数据与大语言模型的医疗模拟场景自动生成方法 large language model
8 Do Large Language Models Understand Conversational Implicature -- A case study with a chinese sitcom 提出SwordsmanImp数据集以解决大语言模型对会话含义理解的挑战 large language model ✅
9 Evaluating Telugu Proficiency in Large Language Models_ A Comparative Analysis of ChatGPT and Gemini 评估大型语言模型在泰卢固语中的能力，比较ChatGPT与Gemini large language model
10 Calibration of Large Language Models on Code Summarization 提出LLM校准方法以解决代码摘要质量评估问题 large language model
11 Game-MUG: Multimodal Oriented Game Situation Understanding and Commentary Generation Dataset 提出GAME-MUG数据集以解决电竞解说理解不足问题 multimodal
12 Graphical Reasoning: LLM-based Semi-Open Relation Extraction 提出基于图形推理的半开放关系抽取方法以提升抽取精度 chain-of-thought
13 RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing 综述检索增强语言模型以解决LLM的知识缺乏问题 large language model ✅
14 HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning 提出HydraLoRA以解决复杂数据集下PEFT性能不足问题 large language model
15 CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification 提出CodeHalu以解决大语言模型中的代码幻觉问题 large language model ✅
16 TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning 提出跨语言后门攻击方法以解决多语言LLM安全问题 large language model
17 RepEval: Effective Text Evaluation with LLM Representation 提出RepEval以解决LLM文本评估的适应性与成本问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
18 Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning 提出奖励校准方法以解决大语言模型的奖励过度优化问题 reinforcement learning large language model
19 Iterative Reasoning Preference Optimization 提出迭代推理偏好优化方法以提升推理任务性能 DPO chain-of-thought
20 Improving Disease Detection from Social Media Text via Self-Augmentation and Contrastive Learning 提出自增强与对比学习结合的方法以提高社交媒体疾病检测 contrastive learning
21 StablePT: Towards Stable Prompting for Few-shot Learning via Input Separation 提出StablePT以解决少样本学习中的提示不稳定性问题 contrastive learning large language model ✅
22 Knowledge Distillation vs. Pretraining from Scratch under a Fixed (Computation) Budget 比较知识蒸馏与从头预训练在固定计算预算下的效果 distillation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页