cs.CL（2024-02-27）

📊 共 37 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) (33 🔗6) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (33 篇)

#题目一句话要点标签🔗⭐
1 Re-Ex: Revising after Explanation Reduces the Factual Errors in LLM Responses 提出Re-Ex以减少大型语言模型响应中的事实错误 large language model
2 Probing Multimodal Large Language Models for Global and Local Semantic Representations 探究多模态大语言模型的全局与局部语义表示 large language model multimodal ✅
3 Deep Learning Detection Method for Large Language Models-Generated Scientific Content 提出AI-Catcher以检测大型语言模型生成的科学内容 large language model multimodal
4 The Foundational Capabilities of Large Language Models in Predicting Postoperative Risks Using Clinical Notes 利用大型语言模型预测术后风险以提升围手术期护理 large language model foundation model
5 MATHSENSEI: A Tool-Augmented Large Language Model for Mathematical Reasoning 提出MathSensei以解决复杂数学推理问题 large language model chain-of-thought ✅
6 The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits 提出1-bit LLM以降低大语言模型的成本与复杂性 large language model
7 Massive Activations in Large Language Models 揭示大语言模型中的大规模激活现象及其影响 large language model ✅
8 Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue 揭示多轮对话中大型语言模型的安全漏洞 large language model
9 Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey 综述大语言模型在表格数据上的应用与挑战 large language model
10 EmMark: Robust Watermarks for IP Protection of Embedded Quantized Large Language Models 提出EmMark以解决嵌入式量化大语言模型的知识产权保护问题 large language model
11 Acquiring Linguistic Knowledge from Multimodal Input 通过多模态输入提升语言模型的数据效率 multimodal
12 Tower: An Open Multilingual Large Language Model for Translation-Related Tasks 提出Tower模型以提升多任务翻译工作流的性能 large language model
13 Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers 提出GPO以优化大语言模型的提示生成 large language model ✅
14 BASES: Large-scale Web Search User Simulation with Large Language Model based Agents 提出BASES框架以解决大规模用户搜索行为模拟问题 large language model
15 Training-Free Long-Context Scaling of Large Language Models 提出双块注意力机制以解决长文本处理问题 large language model ✅
16 Investigating Continual Pretraining in Large Language Models: Insights and Implications 提出持续预训练方法以提升大语言模型的适应性与知识保留 large language model
17 Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models 提出Fact-and-Reflection以改善大语言模型的置信度校准问题 large language model
18 Creating Suspenseful Stories: Iterative Planning with Large Language Models 提出基于迭代提示的规划方法以生成悬念故事 large language model
19 Measuring Vision-Language STEM Skills of Neural Models 提出新数据集以评估神经模型的STEM技能 foundation model multimodal
20 Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data 提出QRData基准以评估LLMs在数据驱动的统计与因果推理能力 large language model chain-of-thought ✅
21 Can GPT-4 Identify Propaganda? Annotation and Detection of Propaganda Spans in News Articles 提出ArPro数据集以解决多语言宣传检测问题 large language model multimodal
22 MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning 提出MELoRA以解决低秩适配器的参数效率问题 large language model instruction following
23 Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems 提出一种方法以解决RAG系统中的数据泄露问题 instruction following
24 LLMGuard: Guarding Against Unsafe LLM Behavior 提出LLMGuard以解决大型语言模型的不安全行为问题 large language model
25 Inducing Generalization across Languages and Tasks using Featurized Low-Rank Mixtures 提出Featurized Low-rank Mixtures以解决多语言多任务适应问题 large language model
26 Adversarial Math Word Problem Generation 提出对抗性数学文字题生成以确保公平评估 large language model
27 Deep Learning Based Named Entity Recognition Models for Recipes 提出基于深度学习的命名实体识别模型以解析食谱文本 large language model
28 Benchmarking GPT-4 on Algorithmic Problems: A Systematic Evaluation of Prompting Strategies 系统评估GPT-4在算法问题上的提示策略 large language model
29 AmbigNLG: Addressing Task Ambiguity in Instruction for NLG 提出AmbigNLG以解决NLG任务中的指令模糊性问题 large language model
30 Beyond prompt brittleness: Evaluating the reliability and consistency of political worldviews in LLMs 提出一系列测试以评估大型语言模型的政治世界观可靠性 large language model
31 SoFA: Shielded On-the-fly Alignment via Priority Rule Following 提出优先规则遵循以解决大语言模型对人类价值观的对齐问题 large language model
32 RECOST: External Knowledge Guided Data-efficient Instruction Tuning 提出RECOST以解决数据高依赖性的问题 large language model
33 Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection 评估大型语言模型在领域外意图检测中的表现 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🔗⭐
34 TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space 提出TruthX以解决大型语言模型的虚假生成问题 contrastive learning large language model
35 Enhancing EEG-to-Text Decoding through Transferable Representations from Pre-trained Contrastive EEG-Text Masked Autoencoder 提出CET-MAE以解决EEG与文本解码的跨模态学习问题 masked autoencoder MAE large language model
36 A Language Model based Framework for New Concept Placement in Ontologies 提出基于语言模型的框架以解决本体中新概念插入问题 contrastive learning large language model

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
37 Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models 提出RiC方法以解决主观任务对话模拟问题 HuMoR large language model chain-of-thought

⬅️ 返回 cs.CL 首页 · 🏠 返回主页