Tag: Few-Shot Learning
All the articles with the tag "Few-Shot Learning".
-
Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning
Published: at 11:24 AM
91.44 🤔本文提出双向对齐（BiAlign）方法，通过对齐学生模型与教师模型的令牌级输出分布和输入偏好，显著提升了学生模型的上下文学习能力，并在多种任务上取得了优于基线的结果。
-
Scalable Model Merging with Progressive Layer-wise Distillation
Published: at 11:26 AM 87.67 🤔本文提出ProDistill算法，通过逐层教师-学生蒸馏高效合并大型预训练模型，理论证明领域特定数据的必要性，并在视觉、语言任务上实现显著性能提升（6.14%-6.61%），展现出优越的内存和计算效率。
-
AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking
Published: at 11:22 AM 87.06 🤔AdaReasoner通过强化学习框架自适应调整大型语言模型的推理配置（生成温度、推理步骤数和指令格式），在多样化任务上显著优于固定配置的基线方法，展现了快速收敛和分布外鲁棒性。
-
Less is More: Enhancing Structured Multi-Agent Reasoning via Quality-Guided Distillation
Published: at 04:28 PM 77.44 🤔本文提出了一种质量导向的多代理框架，通过提示诱导、检索增强合成和奖励过滤从少量标注数据中提炼高质量监督信号，提升LLMs在低资源结构化推理任务中的性能。
-
Latte: Transfering LLMs` Latent-level Knowledge for Few-shot Tabular Learning
Published: at 11:08 AM 77.34 🤔The paper introduces 'Latte', a framework that transfers latent-level knowledge from Large Language Models during training to enhance few-shot tabular learning, outperforming baselines by leveraging unlabeled data and mitigating overfitting across diverse classification and regression tasks.