On the Way to LLM Personalization: Learning to Remember User Conversations
원문 초록
Large Language Models (LLMs) have quickly become an invaluable assistant for a variety of tasks. However, their effectiveness is constrained by their ability to tailor responses to human preferences and behaviors via personalization. Prior work in LLM personalization has largely focused on style transfer or incorporating small factoids about the user, as knowledge injection remains an open challenge. In this paper, we explore injecting knowledge of prior conversations into LLMs to enable future work on less redundant, personalized conversations. We identify two real-world constraints: (1) conversations are sequential in time and must be treated as such during training, and (2) per-user personalization is only viable in parameter-efficient settings. To this aim, we propose PLUM, a pipeline performing data augmentation for up-sampling conversations as question-answer pairs, that are then used to finetune a low-rank adaptation adapter with a weighted cross entropy loss. Even in this first exploration of the problem, we perform competitively with baselines such as RAG, attaining an accuracy of 81.5% across 100 conversations.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
RAG-VisualRec: An Open Resource for Vision- and Text-Enhanced Retrieval-Augmented Generation in Recommendation
Pseudo Multi-Source Domain Generalization: Bridging the Gap Between Single and Multi-Source Domain Generalization
Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression
SenseShift6D: Multimodal RGB-D Benchmarking for Robust 6D Pose Estimation across Environment and Sensor Variations
Developing Visual Augmented Q&A System using Scalable Vision Embedding Retrieval & Late Interaction Re-ranker
AI-Enhanced Pediatric Pneumonia Detection: A CNN-Based Approach Using Data Augmentation and Generative Adversarial Networks (GANs)
토론
이 논문과 연결된 포럼 글이 아직 없습니다.