Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts
When using large language models (LLMs) in knowledge-intensive tasks, such as open-domain question answering, external context can bridge a gap between external knowledge and LLM's parametric knowledge. Recent research has been developed to amplify contextual knowledge over the parametric knowl...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , , , , , , , |
Format | Paper Journal Article |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
02.08.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | When using large language models (LLMs) in knowledge-intensive tasks, such as open-domain question answering, external context can bridge a gap between external knowledge and LLM's parametric knowledge. Recent research has been developed to amplify contextual knowledge over the parametric knowledge of LLM 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. |
---|---|
ISSN: | 2331-8422 |
DOI: | 10.48550/arxiv.2408.01084 |