cs.CL（2024-05-16）

📊 共 22 篇论文 | 🔗 6 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 🔗3)

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

#题目一句话要点标签🔗⭐
1 Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality 提出用于混合现实中细粒度训练的自主多模态工作流 large language model multimodal
2 Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models 提出ClozeGER，利用多模态大语言模型提升语音识别的生成式纠错能力 large language model multimodal
3 Chameleon: Mixed-Modal Early-Fusion Foundation Models Chameleon：一种混合模态早期融合的通用基础模型 foundation model multimodal
4 A Hybrid Framework with Large Language Models for Rare Disease Phenotyping 提出结合大型语言模型和知识库的混合框架，用于罕见病表型分析。 large language model
5 A Systematic Evaluation of Large Language Models for Natural Language Generation Tasks 系统性评估大型语言模型在自然语言生成任务中的表现 large language model
6 LFED: A Literary Fiction Evaluation Dataset for Large Language Models 提出LFED数据集，用于评估大型语言模型在文学小说理解和推理方面的能力 large language model ✅
7 Crowdsourcing with Enhanced Data Quality Assurance: An Efficient Approach to Mitigate Resource Scarcity Challenges in Training Large Language Models for Healthcare 提出增强数据质量保证的众包框架，解决医疗LLM训练中的资源稀缺问题 large language model
8 DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented Dialogues DuetSim：利用双大语言模型构建面向任务型对话的用户模拟器 large language model ✅
9 Can formal argumentative reasoning enhance LLMs performances? 提出MQArgEng，利用计算论证增强大型语言模型性能 large language model
10 Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translation SimulMask：通过注意力掩码微调LLM，实现高效同步翻译 large language model
11 Timeline-based Sentence Decomposition with In-Context Learning for Temporal Fact Extraction 提出基于时间线的句子分解策略TSDRE，用于提升时序事实抽取性能 large language model
12 Revisiting OPRO: The Limitations of Small-Scale LLMs as Optimizers 研究表明小规模LLM在OPRO框架下作为优化器效果受限 large language model
13 CPsyExam: A Chinese Benchmark for Evaluating Psychology using Examinations 提出中文心理学考试基准CPsyExam，用于评估LLM的心理学知识和案例分析能力。 large language model
14 Speaker Verification in Agent-Generated Conversations 提出Agent生成对话中的说话人验证任务，评估LLM角色扮演模型的个性化能力。 large language model
15 StyloAI: Distinguishing AI-Generated Content with Stylometric Analysis StyloAI：利用文体分析区分AI生成内容，性能超越现有方法。 large language model
16 MarkLLM: An Open-Source Toolkit for LLM Watermarking MarkLLM：用于LLM水印技术的开源工具包，促进研究与应用。 large language model ✅
17 IGOT: Information Gain Optimized Tokenizer on Domain Adaptive Pretraining 提出信息增益优化的领域自适应预训练分词器IGOT，提升领域模型效率。 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 Distilling Implicit Multimodal Knowledge into Large Language Models for Zero-Resource Dialogue Generation 提出VIKDF框架，利用隐式多模态知识蒸馏提升零资源对话生成能力 distillation large language model multimodal ✅
19 Enhancing Semantics in Multimodal Chain of Thought via Soft Negative Sampling 提出SNSE-CoT方法，通过软负采样增强多模态CoT语义推理能力，缓解幻觉问题。 contrastive learning multimodal chain-of-thought ✅
20 SynthesizRR: Generating Diverse Datasets with Retrieval Augmentation SynthesizRR：提出检索增强的数据集生成方法，提升小模型蒸馏效果 distillation HuMoR large language model ✅
21 Keep It Private: Unsupervised Privatization of Online Text 提出基于强化学习的文本匿名化框架，提升在线文本隐私保护能力 reinforcement learning large language model
22 Leveraging Human Revisions for Improving Text-to-Layout Models 提出Revision-Aware Reward Models，利用人工修订改进文本到布局生成模型。 reinforcement learning RLHF

⬅️ 返回 cs.CL 首页 · 🏠 返回主页