paper-with-me

Papers

LLM-Oriented Retrieval Tuner

2024-03-04 · Si Sun, Hanqing Zhang, Zhiyuan Liu, Jie Bao, Dawei Song

Dense Retrieval (DR) is now considered as a promising tool to enhance the memorization capacity of Large Language Models (LLM) such as GPT3 and GPT-4 by incorporating external memories. However, due to the paradigm discrepancy between text generation of LLM and DR, it is still an open challenge to integrate the retrieval and generation tasks in a shared LLM. In this paper, we propose an efficient LLM-Oriented Retrieval Tuner, namely LMORT, which decouples DR capacity from base LLM and non-invasively coordinates the optimally aligned and uniform layers of the LLM towards a unified DR space, achieving an efficient and effective DR without tuning the LLM itself. The extensive experiments on six BEIR datasets show that our approach could achieve competitive zero-shot retrieval performance compared to a range of strong DR models while maintaining the generation ability of LLM.

📄 PDF Abstract BibTeX arXiv:2403.01999

Code (0)

등록된 구현이 없습니다.

Tasks

MemorizationRetrievalText Generation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Multi-Head Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

MobileFineTuner: A Mobile-Native Framework for On-Device LLM Fine-Tuning in Real-World Embedded AI Applications

2025-12-09 · Jiaxiang Geng, Lunyu Zhao, Yiyi Lu, Bing Luo arxiv

Large language models (LLMs) are moving from cloud-centric services toward on-device embedded AI, where models interact with private, longitudinal signals sensed from users and their physical environments. Mobile phones …

AutoRAGTuner: A Declarative Framework for Automatic Optimization of RAG Pipelines

2026-05-03 · Xintan Zeng, Yongchao Liu, Yice Luo, Jiajun Zhen arxiv

Retrieval-Augmented Generation (RAG) enhances LLMs, but performance is highly sensitive to complex architecture designs and hyper-parameter configurations, which currently rely on inefficient manual tuning. We present Au…

VDTuner: Automated Performance Tuning for Vector Data Management Systems

2024-04-16 · Tiannuo Yang, Wen Hu, Wangqi Peng, Yusen Li 외

Vector data management systems (VDMSs) have become an indispensable cornerstone in large-scale information retrieval and machine learning systems like large language models. To enhance the efficiency and flexibility of s…

Bayesian OptimizationInformation RetrievalManagement

MindTuner: Cross-Subject Visual Decoding with Visual Fingerprint and Semantic Correction

2024-04-19 · Zixuan Gong, Qi Zhang, Guangyin Bao, Lei Zhu 외

Decoding natural visual scenes from brain activity has flourished, with extensive research in single-subject tasks and, however, less in cross-subject tasks. Reconstructing high-quality images in cross-subject tasks is a…

Image ReconstructionText Retrieval

Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from Backbone

2023-10-30 · NeurIPS 2023 11

Parameter-efficient tuning has become a trend in transferring large-scale foundation models to downstream applications. Existing methods typically embed some light-weight tuners into the backbone, where both the design a…

Disentanglement