paper-with-me

Papers

Decoupled Alignment for Robust Plug-and-Play Adaptation

2024-06-03 · Haozheng Luo, Jiahao Yu, Wenxin Zhang, Jialong Li, Jerry Yao-Chieh Hu, Xinyu Xing, Han Liu

We introduce a low-resource safety enhancement method for aligning large language models (LLMs) without the need for supervised fine-tuning (SFT) or reinforcement learning from human feedback (RLHF). Our main idea is to exploit knowledge distillation to extract the alignment information from existing well-aligned LLMs and integrate it into unaligned LLMs in a plug-and-play fashion. Methodology, we employ delta debugging to identify the critical components of knowledge necessary for effective distillation. On the harmful question dataset, our method significantly enhances the average defense success rate by approximately 14.41%, reaching as high as 51.39%, in 17 unaligned pre-trained LLMs, without compromising performance.

📄 PDF Abstract BibTeX arXiv:2406.01514

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

The Detector Teaches Itself: Lightweight Self-Supervised Adaptation for Open-Vocabulary Object Detection

2026-05-05 · Yazhe Wan, Changjae Oh arxiv

Open-vocabulary object detection aims to recognize objects from an open set of categories, which leverages vision-language models (VLMs) pre-trained on large-scale image-text data. The cooperative paradigm combines an ob…

Object Detection

Empowering Heterogeneous Graph Foundation Models via Decoupled Relation Alignment

2026-05-01 · Ziyu Zheng, Yaming Yang, Zhe Wang, Ziyu Guan 외 arxiv

While Graph Foundation Models (GFMs) have achieved remarkable success in homogeneous graphs, extending them to multi-domain heterogeneous graphs (MDHGs) remains a formidable challenge due to cross-type feature shifts and…

Efficient and Effective Adaptation of Multimodal Foundation Models in Sequential Recommendation

2024-11-05 · Junchen Fu, Xuri Ge, Xin Xin, Alexandros Karatzoglou 외

Multimodal foundation models (MFMs) have revolutionized sequential recommender systems through advanced representation learning. While Parameter-efficient Fine-tuning (PEFT) is commonly used to adapt these models, studie…

GPUparameter-efficient fine-tuningRecommendation SystemsRepresentation Learning+1

Decoupled SGDA for Games with Intermittent Strategy Communication

2025-01-24 · Ali Zindari, Parham Yazdkhasti, Anton Rodomanov, Tatjana Chavdarova 외

We focus on reducing communication overhead in multiplayer games, where frequently exchanging strategies between players is not feasible and players have noisy or outdated strategies of the other players. We introduce De…

Mask the Target: A Plug-and-Play Regularizer Against LoRA Forgetting

2026-05-28 · Runze Xu, Arpit Garg, Hemanth Saratchandran, Simon Lucey arxiv

Low-Rank Adaptation (LoRA) has become one of the most widely used fine-tuning mechanisms for adapting large language models to new domains, tasks, and users. Yet adaptation performance alone can obscure an important fail…