cs.CL（2024-11-06）

📊 共 24 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) (21 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (21 篇)

#题目一句话要点标签🔗⭐
1 From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models 综述词向量到多模态嵌入：大型语言模型的技术、应用与未来方向 large language model multimodal
2 Analyzing Multimodal Features of Spontaneous Voice Assistant Commands for Mild Cognitive Impairment Detection 利用语音助手命令的多模态特征进行轻度认知障碍检测 multimodal
3 Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models 提出多项式组合激活函数PolyCom，提升大语言模型动态性和性能 large language model ✅
4 MEG: Medical Knowledge-Augmented Large Language Models for Question Answering 提出MEG：一种医学知识增强的大语言模型，用于问答任务。 large language model
5 Improving Radiology Report Conciseness and Structure via Local Large Language Models 利用本地大语言模型提升放射科报告的简洁性和结构化程度 large language model
6 M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models 提出M3SciQA多模态多文档科学问答基准，用于评估基础模型在复杂科研场景下的能力。 foundation model
7 QUILL: Quotation Generation Enhancement of Large Language Models QUILL：通过引言生成增强大型语言模型的能力 large language model ✅
8 Deploying Multi-task Online Server with Large Language Model 提出三阶段多任务学习框架，在降低90.9%开销的同时，性能与单任务模型相当。 large language model
9 Diversity Helps Jailbreak Large Language Models 利用多样性提示破解大型语言模型安全限制，显著提升攻击成功率 large language model
10 Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision-Language Models 提出Multi3Hate数据集，揭示多文化背景下视觉-语言模型仇恨言论检测的偏差。 multimodal ✅
11 A Comparative Study of Recent Large Language Models on Generating Hospital Discharge Summaries for Lung Cancer Patients 对比研究大型语言模型在生成肺癌患者出院总结中的表现，发现LLaMA 3具有优势 large language model
12 Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress? 医学领域大语言和视觉语言模型适配研究：领域自适应预训练真的有效吗？ large language model foundation model
13 Number Cookbook: Number Understanding of Language Models and How to Improve It 提出Number Cookbook基准，提升LLM在数值理解和处理方面的能力 large language model chain-of-thought ✅
14 From Medprompt to o1: Exploration of Run-Time Strategies for Medical Challenge Problems and Beyond 探索医学挑战问题：对比Medprompt与o1模型的运行时策略 large language model chain-of-thought
15 Improving Bilingual Capabilities of Language Models to Support Diverse Linguistic Practices in Education 通过改进语言模型的双语能力，支持教育领域中多样化的语言实践 large language model
16 Bottom-Up and Top-Down Analysis of Values, Agendas, and Observations in Corpora and LLMs 提出一种自底向上和自顶向下的方法，用于分析语料库和LLM中的价值观、议程和观察结果。 large language model
17 What Really is Commonsense Knowledge? 提出常识知识统一定义，揭示常识QA数据集中的非常识实例问题 large language model
18 Evaluating Moral Beliefs across LLMs through a Pluralistic Framework 提出三模块框架，评估大型语言模型在道德选择、道德辩论中的道德信念及文化、性别偏见。 large language model
19 Beemo: Benchmark of Expert-edited Machine-generated Outputs Beemo：专家编辑的机器生成文本基准，用于评估多作者场景下的文本溯源。 large language model
20 How Does A Text Preprocessing Pipeline Affect Ontology Matching? 研究文本预处理流程对本体匹配的影响，并提出基于逻辑和LLM的修复方法。 large language model
21 Understanding the Effects of Human-written Paraphrases in LLM-generated Text Detection 提出HLPC数据集，研究人工释义对LLM生成文本检测的影响 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🔗⭐
22 MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba MambaPEFT：探索Mamba模型的高效参数微调方法 Mamba SSM state space model
23 Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models 揭示VLM图像编码器层间安全不对齐，提出层级PPO进行安全对齐 PPO RLHF multimodal
24 The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models 揭示对齐语言模型中性别歧视的持续性：关注性别多样性群体的偏见放大问题 DPO direct preference optimization

⬅️ 返回 cs.CL 首页 · 🏠 返回主页