论文标题：Direct Preference Optimization: Your Language Model is Secretly a R...
投稿
收录了118篇文章 · 26人关注
-
直接偏好优化技术DPO基础理论及推导
-
自适应视图增强的谣言检测图对比学习方法论文标题：Propagation Tree Is Not Deep: Adaptive Graph Contrastive Learning A...
-
生成式大模型的RLHF技术（一）：基础一、概述 大语言模型（LLMs）在预训练的过程中通常会捕捉数据的特征，而这些训练数据通常既包含高质量的也包含低质量的，因此模型有时会产生不被期望...
-
LoRA：大模型下游任务的低秩适应论文标题：LoRA: Low-Rank Adaptation of Large Language Models论文链接：https://arxi...
-
Megatron-LM：Transformer模型专用分布式张量模型并行方法论文标题：Megatron-LM: Training Multi-Billion Parameter Language Models Using...
-
思维树：大模型的复杂推理技术论文标题：Tree of Thoughts: Deliberate Problem Solving with Large Language Mo...
-
LIMA：小规模监督数据指令微调论文标题：LIMA: Less Is More for Alignment论文链接：https://arxiv.org/abs/2305.112...
-
语言模型的自洽性思维链推理技术论文标题：Self-Consistency Improves Chain of Thought Reasoning in Language Mo...
-
GPipe：微批量流水线并行论文标题：GPipe: Easy Scaling with Micro-Batch Pipeline Parallelism论文链接：https...
-
InstructGPT：语言模型的人类反馈指令对齐
论文标题：Training language models to follow instructions with human feedback...
专题公告
人工智能学习频道
{var%20f='http://v.t.sina.com.cn/share/share.php?appkey=1881139527',u=z||d.location,p=['&url=',e(u),'&title=',e(t||d.title),'&source=',e(r),'&sourceUrl=',e(l),'&content=',c||'gb2312','&pic=',e(p||'')].join('');function%20a(){if(!window.open([f,p].join(''),'mb',['toolbar=0,status=0,resizable=1,width=440,height=430,left=',(s.width-440)/2,',top=',(s.height-430)/2].join('')))u.href=[f,p].join('');};if(/Firefox/.test(navigator.userAgent))setTimeout(a,0);else%20a();})(screen,document,encodeURIComponent,'','','https://upload.jianshu.io/collections/images/1904333/%E7%BC%96%E7%A8%8B2.jpg', '推荐专题《人工智能》（ 分享自 @简书 ）','https://jianshuapi.com/c/90f5201e753b?utm_campaign=maleskine&utm_content=collection&utm_medium=reader_share&utm_source=weibo','页面编码gb2312|utf-8默认gb2312'));){kind=link}