cs.CL（2024-04-16）

📊 共 28 篇论文 | 🔗 9 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (24 🔗6) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (24 篇)

#题目一句话要点标签🔗⭐
1 CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity 提出CoTAR以解决LLM输出信息幻觉问题 large language model chain-of-thought
2 Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning 揭示基础大型语言模型在上下文学习中的误用潜力 large language model instruction following
3 Reasoning on Efficient Knowledge Paths:Knowledge Graph Guides Large Language Model for Domain Question Answering 提出知识图谱引导的推理路径选择方法以解决领域问答中的幻觉问题 large language model chain-of-thought
4 HLAT: High-quality Large Language Model Pre-trained on AWS Trainium 提出HLAT以解决AWS Trainium上大语言模型训练的挑战 large language model ✅
5 Improving the Capabilities of Large Language Model Based Marketing Analytics Copilots With Semantic Search And Fine-Tuning 通过语义搜索与微调提升大语言模型在营销分析中的能力 large language model
6 Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training 提出BLOOMZMMS以解决多语言语音理解问题 large language model
7 ViTextVQA: A Large-Scale Visual Question Answering Dataset and a Novel Multimodal Feature Fusion Method for Vietnamese Text Comprehension in Images 提出ViTextVQA数据集与ViTextBLIP-2方法以解决越南文本理解问题 multimodal
8 Construction of Domain-specified Japanese Large Language Model for Finance through Continual Pre-training 构建针对金融领域的日语大语言模型以提升金融文本处理能力 large language model
9 Enhancing Confidence Expression in Large Language Models Through Learning from Past Experience 提出LePe方法以提升大型语言模型的信心表达能力 large language model
10 Balancing Speciality and Versatility: A Coarse to Fine Framework for Mitigating Catastrophic Forgetting in Large Language Models 提出CoFiTune框架以解决大语言模型的灾难性遗忘问题 large language model ✅
11 Generative Text Steganography with Large Language Model 提出LLM-Stega以解决大语言模型下的文本隐写问题 large language model
12 Deep Learning and LLM-based Methods Applied to Stellar Lightcurve Classification 提出深度学习与LLM方法以自动分类恒星光变曲线 large language model multimodal
13 Autoregressive Pre-Training on Pixels and Texts 提出基于像素和文本的自回归预训练方法以提升语言模型性能 multimodal ✅
14 Forcing Diffuse Distributions out of Language Models 提出一种微调方法以解决语言模型输出分布不均问题 large language model
15 A LayoutLMv3-Based Model for Enhanced Relation Extraction in Visually-Rich Documents 提出基于LayoutLMv3的模型以增强视觉丰富文档中的关系提取 multimodal
16 Fewer Truncations Improve Language Modeling 提出最佳适配打包方法以解决语言模型训练中的截断问题 large language model
17 Uncovering Latent Arguments in Social Media Messaging by Employing LLMs-in-the-Loop Strategy 提出LLMs-in-the-Loop策略以解决社交媒体论点发现问题 large language model
18 Can Language Models Solve Olympiad Programming? 提出USACO基准以评估语言模型在编程竞赛中的表现 chain-of-thought
19 White Men Lead, Black Women Help? Benchmarking and Mitigating Language Agency Social Biases in LLMs 提出语言代理偏见评估基准以解决LLM中的社会偏见问题 large language model
20 When Emotional Stimuli meet Prompt Designing: An Auto-Prompt Graphical Paradigm 提出自动提示图形范式以提升大语言模型的解决能力 large language model
21 DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion 提出DeStein以解决语言模型毒性输出问题 large language model ✅
22 CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting 提出CULTURE-GEN以揭示语言模型中的全球文化认知 large language model ✅
23 ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence 提出ClashEval以量化LLM内部先验与外部证据的冲突 large language model
24 Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards 提出Self-Explore以解决LLM推理能力自我提升问题 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
25 Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study 比较DPO与PPO在大语言模型对齐中的优劣 reinforcement learning PPO RLHF ✅
26 Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations 基于不确定性的放弃策略提升LLM安全性与减少幻觉现象 reinforcement learning RLHF large language model
27 Self-playing Adversarial Language Game Enhances LLM Reasoning 通过自我对弈对抗语言游戏提升大语言模型推理能力 reinforcement learning large language model ✅
28 Grounded Language Agent for Product Search via Intelligent Web Interactions 提出GLAINTEL以解决高成本大模型交互问题 reinforcement learning large language model ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页