paper-with-me

홈 › Papers

KnowPrefix-Tuning: A Two-Stage Prefix-Tuning Framework for Knowledge-Grounded Dialogue Generation

2023-06-27 · Jiaqi Bai, Zhao Yan, Jian Yang, Xinnian Liang, Hongcheng Guo, Zhoujun Li

Existing knowledge-grounded conversation systems generate responses typically in a retrieve-then-generate manner. They require a large knowledge base and a strong knowledge retrieval component, which is time- and resource-consuming. In this paper, we address the challenge by leveraging the inherent knowledge encoded in the pre-trained language models (PLMs). We propose Knowledgeable Prefix Tuning (KnowPrefix-Tuning), a two-stage tuning framework, bypassing the retrieval process in a knowledge-grounded conversation system by injecting prior knowledge into the lightweight knowledge prefix. The knowledge prefix is a sequence of continuous knowledge-specific vectors that can be learned during training. In addition, we propose a novel interactive re-parameterization mechanism that allows the prefix to interact fully with the PLM during the optimization of response generation. Experimental results demonstrate that KnowPrefix-Tuning outperforms fine-tuning and other lightweight tuning approaches, and performs comparably with strong retrieval-based baselines while being $3\times$ faster during inference.

📄 PDF Abstract BibTeX arXiv:2306.15430

Code (1)

fantast4ever/knowprefix-tuning 공식 구현 pytorch

Tasks

Dialogue GenerationResponse GenerationRetrieval

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

On Robust Prefix-Tuning for Text Classification

2022-03-19 · ICLR 2022 4 · Zonghan Yang, Yang Liu

Recently, prefix-tuning has gained increasing attention as a parameter-efficient finetuning method for large-scale pretrained language models. The method keeps the pretrained models fixed and only updates the prefix toke…

ClassificationLanguage Modellingtext-classificationText Classification

The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models

2025-03-04 · Ke Ji, Jiahao Xu, Tian Liang, Qiuzhi Liu 외

Improving the reasoning capabilities of large language models (LLMs) typically requires supervised fine-tuning with labeled data or computationally expensive sampling. We introduce Unsupervised Prefix Fine-Tuning (UPFT),…

Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning

2022-10-26 · Yifan Chen, Devamanyu Hazarika, Mahdi Namazifar, Yang Liu 외

Prefix-tuning, or more generally continuous prompt tuning, has become an essential paradigm of parameter-efficient transfer learning. Using a large pre-trained language model (PLM), prefix-tuning can obtain strong perfor…

Language ModelingLanguage ModellingNatural Language UnderstandingTransfer Learning

Prefix-Tuning+: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention

2025-06-16 · Haonan Wang, Brian Chen, Siquan Li, Xinhe Liang 외

Parameter-Efficient Fine-Tuning (PEFT) methods have become crucial for rapidly adapting large language models (LLMs) to downstream tasks. Prefix-Tuning, an early and effective PEFT technique, demonstrated the ability to …

parameter-efficient fine-tuning

Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning

2025-11-13 · Sirui Liang, Pengfei Cao, Jian Zhao, Cong Huang 외 arxiv

Parameter-Efficient finetuning (PEFT) enhances model performance on downstream tasks by updating a minimal subset of parameters. Representation finetuning (ReFT) methods further improve efficiency by freezing model weigh…

Mathematical Reasoning