Tag: Fine-tuning

All the articles with the tag "Fine-tuning".

• Layered Unlearning for Adversarial Relearning

  Published: 19 May, 2025 |  at  11:17 AM

  

  77.78 🤔

  本文提出分层遗忘（Layered Unlearning, LU）方法，通过多阶段逐步遗忘数据子集并诱导不同抑制机制，增强大型语言模型对对抗性重新学习的鲁棒性，尽管对语料库攻击仍显脆弱。

• Less is More: Enhancing Structured Multi-Agent Reasoning via Quality-Guided Distillation

  Published: 4 May, 2025 |  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: 11 May, 2025 |  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.

• COSMOS: Predictable and Cost-Effective Adaptation of LLMs

  Published: 10 May, 2025 |  at  11:05 AM

  

  75.99 🤔

  COSMOS introduces a cost-effective framework to predict performance and cost of LLM adaptation strategies like QLoRA fine-tuning and retrieval-augmented ICL, achieving high accuracy (1.09% MAE) and reducing computational costs by 92.72% across eight diverse benchmarks.

• The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)

  Published: 4 May, 2025 |  at  04:33 PM

  

  75.58 🤔

  本文通过提出位置 ID 操纵的 PFT 方法，揭示并解决了 LLM 在角色分离学习中依赖捷径的问题，提高了模型的鲁棒性和安全性，同时保持了性能。