cs.CL（2024-03-29）

📊 共 22 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (20 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1)

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

#题目一句话要点标签🔗⭐
1 LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model 提出LLaVA-Gemma以加速多模态基础模型的训练 large language model foundation model multimodal
2 DataAgent: Evaluating Large Language Models' Ability to Answer Zero-Shot, Natural Language Queries 提出DataAgent以解决数据科学家数据分析效率低下问题 large language model chain-of-thought
3 MANGO: A Benchmark for Evaluating Mapping and Navigation Abilities of Large Language Models 提出MANGO基准以评估大语言模型的映射与导航能力 large language model ✅
4 Explaining Large Language Models Decisions Using Shapley Values 基于Shapley值解释大型语言模型决策以解决人类行为模拟问题 large language model
5 On Large Language Models' Hallucination with Regard to Known Facts 提出基于推理动态的LLM幻觉检测方法以解决知识错误问题 large language model
6 Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs 提出Transformer-Lite以解决移动设备上LLM高效部署问题 large language model
7 Large Language Model based Situational Dialogues for Second Language Learning 提出基于大语言模型的情境对话以解决第二语言学习问题 large language model
8 Measuring Taiwanese Mandarin Language Understanding 提出TMLU评估套件以解决台湾普通话LLM评估不足问题 large language model chain-of-thought
9 Constructing Multilingual Visual-Text Datasets Revealing Visual Multilingual Ability of Vision Language Models 构建多语言视觉文本数据集以揭示视觉语言模型的多语言能力 large language model
10 Latxa: An Open Language Model and Evaluation Suite for Basque 提出Latxa以解决巴斯克语大语言模型的稀缺问题 large language model
11 Using LLMs to Model the Beliefs and Preferences of Targeted Populations 提出使用LLM建模目标人群信念与偏好以解决行为模拟问题 large language model
12 Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning 通过调优和多分支推理提升低参数LLM的通用智能体能力 large language model
13 Towards a Robust Retrieval-Based Summarization System 提出LogicSumm与SummRAG以提升LLM在摘要生成中的鲁棒性 large language model
14 GPTA: Generative Prompt Tuning Assistant for Synergistic Downstream Neural Network Enhancement with LLMs 提出GPTA框架以解决LLM在下游任务训练中的安全性问题 large language model
15 Classifying Conspiratorial Narratives At Scale: False Alarms and Erroneous Connections 提出基于BERT的模型以分类阴谋论讨论 large language model
16 LUQ: Long-text Uncertainty Quantification for LLMs 提出LUQ以解决长文本生成的不确定性量化问题 large language model
17 IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Context 提出IndiBias以评估印度语境下语言模型的社会偏见 large language model
18 User Modeling Challenges in Interactive AI Assistant Systems 分析用户心理状态以提升互动AI助手的个性化指导 large language model
19 Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning 提出CoTErrorSet以提升LLMs从错误中学习的能力 chain-of-thought ✅
20 Are LLMs Effective Backbones for Fine-tuning? An Experimental Investigation of Supervised LLMs on Chinese Short Text Matching 通过实验分析优化LLMs在中文短文本匹配中的微调效果 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🔗⭐
21 DiJiang: Efficient Large Language Models through Compact Kernelization 提出DiJiang以降低大语言模型的计算负担 linear attention large language model ✅
22 Gecko: Versatile Text Embeddings Distilled from Large Language Models 提出Gecko以解决文本嵌入模型的高效性问题 distillation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页