PERSOMA: PERsonalized SOft ProMpt Adapter Architecture for Personalized Language Prompting
Understanding the nuances of a user's extensive interaction history is key to building accurate and personalized natural language systems that can adapt to evolving user preferences. To address this, we introduce PERSOMA, Personalized Soft Prompt Adapter architecture. Unlike previous personalized prompting methods for large language models, PERSOMA offers a novel approach to efficiently capture user history. It achieves this by resampling and compressing interactions as free form text into expressive soft prompt embeddings, building upon recent research utilizing embedding representations as input for LLMs. We rigorously validate our approach by evaluating various adapter architectures, first-stage sampling strategies, parameter-efficient tuning techniques like LoRA, and other personalization methods. Our results demonstrate PERSOMA's superior ability to handle large and complex user histories compared to existing embedding-based and text-prompt-based techniques.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Don't Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs
Personalization in Large Language Models (LLMs) often relies on user-specific soft prompts. However, these prompts become obsolete when the foundation model is upgraded, necessitating costly, full-scale retraining. To ov…
MIP: CLIP-based Image Reconstruction from PEFT Gradients
Contrastive Language-Image Pre-training (CLIP) model, as an effective pre-trained multimodal neural network, has been widely used in distributed machine learning tasks, especially Federated Learning (FL). Typically, CLIP…
Federated LearningImage Reconstructionparameter-efficient fine-tuningReconstruction AttackConceptrol: Concept Control of Zero-shot Personalized Image Generation
Personalized image generation with text-to-image diffusion models generates unseen images based on reference image content. Zero-shot adapter methods such as IP-Adapter and OminiControl are especially interesting because…
Image GenerationPersonalized Image GenerationLynx: Towards High-Fidelity Personalized Video Generation
We present Lynx, a high-fidelity model for personalized video synthesis from a single input image. Built on an open-source Diffusion Transformer (DiT) foundation model, Lynx introduces two lightweight adapters to ensure …
Video GenerationSoft Language Prompts for Language Transfer
Cross-lingual knowledge transfer, especially between high- and low-resource languages, remains challenging in natural language processing (NLP). This study offers insights for improving cross-lingual NLP applications thr…
Cross-Lingual Transferparameter-efficient fine-tuningTransfer Learning