Tag: Robustness

All the articles with the tag "Robustness".

• Do LLMs Memorize Recommendation Datasets? A Preliminary Study on MovieLens-1M

  Published: 19 May, 2025 |  at  11:16 AM

  

  83.59 🤔

  本文通过基于提示的方法初步研究了大型语言模型（LLMs）对MovieLens-1M推荐数据集的记忆程度，发现所有测试模型均表现出一定记忆，且记忆程度与推荐性能和模型规模正相关，同时揭示了流行度偏见问题。

• 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。

• MOOSComp: Improving Lightweight Long-Context Compressor via Mitigating Over-Smoothing and Incorporating Outlier Scores

  Published: 4 May, 2025 |  at  04:29 PM

  

  77.68 🤔

  本文提出MOOSComp方法，通过在训练中添加inter-class cosine similarity loss缓解over-smoothing问题，并在压缩中整合outlier分数保留关键token，显著提升了任务无关的长上下文压缩性能和泛化能力。

• Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes

  Published: 12 May, 2025 |  at  11:14 AM

  

  76.90 🤔

  This paper introduces Latent Preference Coding (LPC), a framework that uses discrete latent codes to model multifaceted human preferences, consistently improving the performance of offline alignment algorithms like DPO, SimPO, and IPO across multiple LLMs and 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。