Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Baek, Ingeol, Chang, Hwan, Kim, Byeongjeong, Lee, Jimin, Lee, Hwanhee
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909513528901632
author Baek, Ingeol
Chang, Hwan
Kim, Byeongjeong
Lee, Jimin
Lee, Hwanhee
author_facet Baek, Ingeol
Chang, Hwan
Kim, Byeongjeong
Lee, Jimin
Lee, Hwanhee
contents Retrieval-Augmented Generation (RAG) enhances language models by retrieving and incorporating relevant external knowledge. However, traditional retrieve-and-generate processes may not be optimized for real-world scenarios, where queries might require multiple retrieval steps or none at all. In this paper, we propose a Probing-RAG, which utilizes the hidden state representations from the intermediate layers of language models to adaptively determine the necessity of additional retrievals for a given query. By employing a pre-trained prober, Probing-RAG effectively captures the model's internal cognition, enabling reliable decision-making about retrieving external documents. Experimental results across five open-domain QA datasets demonstrate that Probing-RAG outperforms previous methods while reducing the number of redundant retrieval steps.
format Preprint
id arxiv_https___arxiv_org_abs_2410_13339
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval
Baek, Ingeol
Chang, Hwan
Kim, Byeongjeong
Lee, Jimin
Lee, Hwanhee
Computation and Language
Retrieval-Augmented Generation (RAG) enhances language models by retrieving and incorporating relevant external knowledge. However, traditional retrieve-and-generate processes may not be optimized for real-world scenarios, where queries might require multiple retrieval steps or none at all. In this paper, we propose a Probing-RAG, which utilizes the hidden state representations from the intermediate layers of language models to adaptively determine the necessity of additional retrievals for a given query. By employing a pre-trained prober, Probing-RAG effectively captures the model's internal cognition, enabling reliable decision-making about retrieving external documents. Experimental results across five open-domain QA datasets demonstrate that Probing-RAG outperforms previous methods while reducing the number of redundant retrieval steps.
title Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval
topic Computation and Language
url https://arxiv.org/abs/2410.13339