cs.CL（2024-03-27）

📊 共 20 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) (14 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective 提出因果框架以量化和缓解多模态大语言模型中的单模态偏差问题 large language model multimodal ✅
2 Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction 提出LMTraj以解决行人轨迹预测问题 foundation model multimodal ✅
3 Dual Instruction Tuning with Large Language Models for Mathematical Reasoning 提出双重指令调优策略以解决数学推理中的生成问题 large language model chain-of-thought
4 Evaluating Large Language Models for Health-Related Text Classification Tasks with Public Social Media Data 提出基于LLM的健康相关文本分类方法以提升社交媒体数据处理效果 large language model
5 A Survey on Large Language Models from Concept to Implementation 调查大型语言模型的应用与实现 large language model
6 Long-form factuality in large language models 提出SAFE方法以提升大型语言模型的长文本事实准确性 large language model ✅
7 Measuring Political Bias in Large Language Models: What Is Said and How It Is Said 提出政治偏见测量方法以解决大型语言模型的透明性问题 large language model
8 The Invalsi Benchmarks: measuring Linguistic and Mathematical understanding of Large Language Models in Italian 提出Invalsi基准以评估意大利语大型语言模型的理解能力 large language model
9 BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models 提出BLADE框架以增强大型语言模型在特定领域的表现 large language model
10 Moderating Illicit Online Image Promotion for Unsafe User-Generated Content Games Using Large Vision-Language Models 提出UGCG-Guard以解决不安全用户生成内容游戏的非法推广问题 chain-of-thought
11 "Sorry, Come Again?" Prompting -- Enhancing Comprehension and Diminishing Hallucination with [PAUSE]-injected Optimal Paraphrasing 提出SCA提示方法以减少LLM幻觉现象 large language model
12 CAUSE: Counterfactual Assessment of User Satisfaction Estimation in Task-Oriented Dialogue Systems 提出基于反事实生成的用户满意度评估方法以解决对话系统中的数据不平衡问题 large language model
13 SDSAT: Accelerating LLM Inference through Speculative Decoding with Semantic Adaptive Tokens 提出SDSAT以加速大语言模型推理过程 large language model ✅
14 TriviaHG: A Dataset for Automatic Hint Generation from Factoid Questions 提出TriviaHG数据集以解决自动提示生成问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
15 Improving Attributed Text Generation of Large Language Models via Preference Learning 通过偏好学习提升大语言模型的属性文本生成能力 preference learning large language model
16 IterAlign: Iterative Constitutional Alignment of Large Language Models 提出IterAlign以解决大型语言模型对齐人类价值观的问题 reinforcement learning RLHF large language model
17 RankMamba: Benchmarking Mamba's Document Ranking Performance in the Era of Transformers 评估Mamba模型在文档排序任务中的表现 Mamba state space model ✅
18 Is Modularity Transferable? A Case Study through the Lens of Knowledge Distillation 提出知识蒸馏方法以实现模块化组件的跨模型迁移 distillation
19 Improving Content Recommendation: Knowledge Graph-Based Semantic Contrastive Learning for Diversity and Cold-Start Users 提出基于知识图谱的对比学习以解决推荐系统的多样性与冷启动问题 contrastive learning
20 Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback 提出RLKF框架以提高大型语言模型的可靠性 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页