Entropy-Based Decoding for Retrieval-Augmented Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qiu, Zexuan, Ou, Zijing, Wu, Bin, Li, Jingjing, Liu, Aiwei, King, Irwin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929716439547904
author Qiu, Zexuan
Ou, Zijing
Wu, Bin
Li, Jingjing
Liu, Aiwei
King, Irwin
author_facet Qiu, Zexuan
Ou, Zijing
Wu, Bin
Li, Jingjing
Liu, Aiwei
King, Irwin
contents Augmenting Large Language Models (LLMs) with retrieved external knowledge has proven effective for improving the factual accuracy of generated responses. Despite their success, retrieval-augmented LLMs still face the distractibility issue, where the generated responses are negatively influenced by noise from both external and internal knowledge sources. In this paper, we introduce a novel, training-free decoding method guided by entropy considerations to mitigate this issue. Our approach utilizes entropy-based document-parallel ensemble decoding to prioritize low-entropy distributions from retrieved documents, thereby enhancing the extraction of relevant information of context. Additionally, it incorporates a contrastive decoding mechanism that contrasts the obtained low-entropy ensemble distribution with the high-entropy distribution derived from the model's internal knowledge across layers, which ensures a greater emphasis on reliable external information. Extensive experiments on open-domain question answering datasets demonstrate the superiority of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2406_17519
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Entropy-Based Decoding for Retrieval-Augmented Large Language Models
Qiu, Zexuan
Ou, Zijing
Wu, Bin
Li, Jingjing
Liu, Aiwei
King, Irwin
Computation and Language
Augmenting Large Language Models (LLMs) with retrieved external knowledge has proven effective for improving the factual accuracy of generated responses. Despite their success, retrieval-augmented LLMs still face the distractibility issue, where the generated responses are negatively influenced by noise from both external and internal knowledge sources. In this paper, we introduce a novel, training-free decoding method guided by entropy considerations to mitigate this issue. Our approach utilizes entropy-based document-parallel ensemble decoding to prioritize low-entropy distributions from retrieved documents, thereby enhancing the extraction of relevant information of context. Additionally, it incorporates a contrastive decoding mechanism that contrasts the obtained low-entropy ensemble distribution with the high-entropy distribution derived from the model's internal knowledge across layers, which ensures a greater emphasis on reliable external information. Extensive experiments on open-domain question answering datasets demonstrate the superiority of our method.
title Entropy-Based Decoding for Retrieval-Augmented Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2406.17519