cs.CL（2023-11-30）

📊 共 17 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) (15 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#题目一句话要点标签🔗⭐
1 Applying Large Language Models and Chain-of-Thought for Automatic Scoring 利用大语言模型和思维链实现自动评分以解决教育评估问题 large language model chain-of-thought
2 mPLUG-PaperOwl: Scientific Diagram Analysis with the Multimodal Large Language Model 提出mPLUG-PaperOwl以增强多模态大语言模型的科学图表分析能力 large language model multimodal ✅
3 AlignBench: Benchmarking Chinese Alignment of Large Language Models 提出AlignBench以评估中文大语言模型的对齐能力 large language model chain-of-thought ✅
4 Consensus, dissensus and synergy between clinicians and specialist foundation models in radiology report generation 提出Flamingo-CXR以解决放射科报告生成中的临床质量评估问题 foundation model
5 Evaluating Large Language Model Creativity from a Literary Perspective 评估大型语言模型在创作写作中的辅助能力 large language model
6 TaskBench: Benchmarking Large Language Models for Task Automation 提出TaskBench以解决大语言模型任务自动化评估问题 large language model
7 CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation 提出CritiqueLLM以解决现有语言模型评价不足问题 large language model
8 ArcMMLU: A Library and Information Science Benchmark for Large Language Models 提出ArcMMLU以评估大型语言模型在图书馆与信息科学领域的能力 large language model
9 ArthModel: Enhance Arithmetic Skills to Large Language Model 提出ArthModel以增强大语言模型的算术能力 large language model ✅
10 Automatic Construction of a Korean Toxic Instruction Dataset for Ethical Tuning of Large Language Models 提出KoTox数据集以提升大型语言模型的伦理调优能力 large language model
11 FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity 提出FFT基准以评估大型语言模型的无害性 large language model instruction following
12 Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text 提出Scrambled Bench以评估GPT-4对混乱文本的处理能力 large language model
13 What Do Llamas Really Think? Revealing Preference Biases in Language Model Representations 提出逻辑布拉德利-特里探测器以揭示语言模型的偏见 large language model ✅
14 Evaluating the Rationale Understanding of Critical Reasoning in Logical Reading Comprehension 提出逻辑阅读理解中的推理理解评估数据集 large language model
15 COVID-19 Vaccine Misinformation in Middle Income Countries 提出多语言数据集以解决中等收入国家疫苗虚假信息问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
16 LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models 提出LMRL-Gym基准以解决多轮强化学习中的语言模型训练问题 reinforcement learning large language model
17 IAG: Induction-Augmented Generation Framework for Answering Reasoning Questions 提出IAG框架以解决隐式推理问题 distillation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页