Saved in:
Bibliographic Details
Main Authors: Kim, Youna, Kim, Hyuhng Joon, Park, Cheonbok, Park, Choonghyun, Cho, Hyunsoo, Kim, Junyeob, Yoo, Kang Min, Lee, Sang-goo, Kim, Taeuk
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.01084
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929529887391744
author Kim, Youna
Kim, Hyuhng Joon
Park, Cheonbok
Park, Choonghyun
Cho, Hyunsoo
Kim, Junyeob
Yoo, Kang Min
Lee, Sang-goo
Kim, Taeuk
author_facet Kim, Youna
Kim, Hyuhng Joon
Park, Cheonbok
Park, Choonghyun
Cho, Hyunsoo
Kim, Junyeob
Yoo, Kang Min
Lee, Sang-goo
Kim, Taeuk
contents When using large language models (LLMs) in knowledge-intensive tasks, such as open-domain question answering, external context can bridge the gap between external knowledge and the LLMs' parametric knowledge. Recent research has been developed to amplify contextual knowledge over the parametric knowledge of LLMs with contrastive decoding approaches. While these approaches could yield truthful responses when relevant context is provided, they are prone to vulnerabilities when faced with noisy contexts. We extend the scope of previous studies to encompass noisy contexts and propose adaptive contrastive decoding (ACD) to leverage contextual influence effectively. ACD demonstrates improvements in open-domain question answering tasks compared to baselines, especially in robustness by remaining undistracted by noisy contexts in retrieval-augmented generation.
format Preprint
id arxiv_https___arxiv_org_abs_2408_01084
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts
Kim, Youna
Kim, Hyuhng Joon
Park, Cheonbok
Park, Choonghyun
Cho, Hyunsoo
Kim, Junyeob
Yoo, Kang Min
Lee, Sang-goo
Kim, Taeuk
Computation and Language
When using large language models (LLMs) in knowledge-intensive tasks, such as open-domain question answering, external context can bridge the gap between external knowledge and the LLMs' parametric knowledge. Recent research has been developed to amplify contextual knowledge over the parametric knowledge of LLMs with contrastive decoding approaches. While these approaches could yield truthful responses when relevant context is provided, they are prone to vulnerabilities when faced with noisy contexts. We extend the scope of previous studies to encompass noisy contexts and propose adaptive contrastive decoding (ACD) to leverage contextual influence effectively. ACD demonstrates improvements in open-domain question answering tasks compared to baselines, especially in robustness by remaining undistracted by noisy contexts in retrieval-augmented generation.
title Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts
topic Computation and Language
url https://arxiv.org/abs/2408.01084