cs.CL（2024-08-09）

📊 共 23 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (20 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (20 篇)

#题目一句话要点标签🔗⭐
1 MSG-Chart: Multimodal Scene Graph for ChartQA 提出MSG-Chart，利用多模态场景图解决图表问答中的结构与语义理解难题。 multimodal
2 From Text to Insight: Leveraging Large Language Models for Performance Evaluation in Management 利用大型语言模型提升管理领域绩效评估的客观性 large language model
3 Order Matters in Hallucination: Reasoning Order as Benchmark and Reflexive Prompting for Large-Language-Models 提出基于推理顺序一致性的LLM评测基准与自反提示策略，解决幻觉问题 large language model
4 ProFuser: Progressive Fusion of Large Language Models ProFuser：通过渐进式融合提升大型语言模型性能 large language model
5 Multi-Turn Interactions for Text-to-SQL with Large Language Models 提出Interactive-T2S框架，通过与数据库交互提升大语言模型Text-to-SQL能力。 large language model
6 GlitchProber: Advancing Effective Detection and Mitigation of Glitch Tokens in Large Language Models GlitchProber：提升大语言模型中Glitch Token的检测与缓解效果 large language model
7 Evaluating the capability of large language models to personalize science texts for diverse middle-school-age learners 评估大型语言模型个性化定制中学科学教材的能力 large language model
8 Large Language Models and Thematic Analysis: Human-AI Synergy in Researching Hate Speech on Social Media 利用大型语言模型进行主题分析，探索人机协同在社交媒体仇恨言论研究中的潜力。 large language model
9 Towards a Generative Approach for Emotion Detection and Reasoning 提出一种基于生成式问答的大语言模型情感检测与推理方法 large language model chain-of-thought
10 Tabular Transfer Learning via Prompting LLMs 提出P2T框架，利用LLM提示实现表格数据的跨领域迁移学习。 large language model ✅
11 KIF: Knowledge Identification and Fusion for Language Model Continual Learning 提出KIF框架，通过知识识别与融合提升语言模型持续学习能力，解决灾难性遗忘问题。 large language model
12 LLaMA based Punctuation Restoration With Forward Pass Only Decoding 提出基于LLaMA和FPOD的标点恢复方法，显著提升推理速度。 large language model
13 DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts 提出DataNarrative框架，利用多智能体LLM自动生成数据驱动的故事，包含可视化和文本。 large language model
14 A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning 提出混合RAG系统以增强复杂推理能力 large language model
15 How Well Do LLMs Identify Cultural Unity in Diversity? 提出CUNIT基准数据集，评估大语言模型对跨文化概念统一性的理解能力 large language model
16 Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts 提出MCA，通过对比提示实现解码时可控的多目标对齐，无需梯度训练。 large language model
17 Examining the Behavior of LLM Architectures Within the Framework of Standardized National Exams in Brazil 利用巴西高考数据集，对比分析LLM与不同社会经济群体在考试中的表现及偏差 large language model
18 Get Confused Cautiously: Textual Sequence Memorization Erasure with Selective Entropy Maximization 提出基于选择性熵最大化的文本序列记忆擦除框架，提升LLM的隐私保护能力。 large language model
19 Synergizing Unsupervised Episode Detection with LLMs for Large-Scale News Events EpiMine：结合无监督事件片段检测与LLM，用于大规模新闻事件分析 large language model
20 FUSE-ing Language Models: Zero-Shot Adapter Discovery for Prompt Optimization Across Tokenizers 提出FUSE，通过零样本适配器发现实现跨分词器的提示优化。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
21 Improving Mortality Prediction After Radiotherapy with Large Language Model Structuring of Large-Scale Unstructured Electronic Health Records RT-Surv框架利用大语言模型结构化电子病历，提升放疗后生存预测精度。 predictive model large language model
22 A Psychology-based Unified Dynamic Framework for Curriculum Learning 提出基于心理学的统一动态课程学习框架PUDF，提升大语言模型微调效果。 MAE curriculum learning large language model
23 reCSE: Portable Reshaping Features for Sentence Embedding in Self-supervised Contrastive Learning 提出reCSE：一种基于特征重塑的自监督对比学习句子嵌入框架 contrastive learning ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页