Large language models as source planner for personalized knowledge-grounded dialogues
Open-domain dialogue system usually requires different sources of knowledge to generate more informative and evidential responses. However, existing knowledge-grounded dialogue systems either focus on a single knowledge source or overlook the dependency between multiple sources of knowledge, which m...
Saved in:
Main Authors: | , , , , , , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2023
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9121 https://ink.library.smu.edu.sg/context/sis_research/article/10124/viewcontent/2023.findings_emnlp.641.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-10124 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-101242024-08-01T14:35:06Z Large language models as source planner for personalized knowledge-grounded dialogues WANG, Hongru HU, Minda DENG, Yang WANG, Rui MI, Fei WANG, Weichao WANG, Yasheng KWAN, Wai-Chung KING, Irwin WONG, Kam-Fai Open-domain dialogue system usually requires different sources of knowledge to generate more informative and evidential responses. However, existing knowledge-grounded dialogue systems either focus on a single knowledge source or overlook the dependency between multiple sources of knowledge, which may result in generating inconsistent or even paradoxical responses. To incorporate multiple knowledge sources and dependencies between them, we propose SAFARI, a novel framework that leverages the exceptional capabilities of large language models (LLMs) in planning, understanding, and incorporating under both supervised and unsupervised settings. Specifically, SAFARI decouples the knowledge grounding into multiple sources and response generation, which allows easy extension to various knowledge sources including the possibility of not using any sources. To study the problem, we construct a personalized knowledge-grounded dialogue dataset Knowledge Behind Persona (KBP), which is the first to consider the dependency between persona and implicit knowledge. Experimental results on the KBP dataset demonstrate that the SAFARI framework can effectively produce persona-consistent and knowledge-enhanced responses. 2023-12-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9121 info:doi/10.18653/v1/2023.findings-emnlp.641 https://ink.library.smu.edu.sg/context/sis_research/article/10124/viewcontent/2023.findings_emnlp.641.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems Programming Languages and Compilers |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Databases and Information Systems Programming Languages and Compilers |
spellingShingle |
Databases and Information Systems Programming Languages and Compilers WANG, Hongru HU, Minda DENG, Yang WANG, Rui MI, Fei WANG, Weichao WANG, Yasheng KWAN, Wai-Chung KING, Irwin WONG, Kam-Fai Large language models as source planner for personalized knowledge-grounded dialogues |
description |
Open-domain dialogue system usually requires different sources of knowledge to generate more informative and evidential responses. However, existing knowledge-grounded dialogue systems either focus on a single knowledge source or overlook the dependency between multiple sources of knowledge, which may result in generating inconsistent or even paradoxical responses. To incorporate multiple knowledge sources and dependencies between them, we propose SAFARI, a novel framework that leverages the exceptional capabilities of large language models (LLMs) in planning, understanding, and incorporating under both supervised and unsupervised settings. Specifically, SAFARI decouples the knowledge grounding into multiple sources and response generation, which allows easy extension to various knowledge sources including the possibility of not using any sources. To study the problem, we construct a personalized knowledge-grounded dialogue dataset Knowledge Behind Persona (KBP), which is the first to consider the dependency between persona and implicit knowledge. Experimental results on the KBP dataset demonstrate that the SAFARI framework can effectively produce persona-consistent and knowledge-enhanced responses. |
format |
text |
author |
WANG, Hongru HU, Minda DENG, Yang WANG, Rui MI, Fei WANG, Weichao WANG, Yasheng KWAN, Wai-Chung KING, Irwin WONG, Kam-Fai |
author_facet |
WANG, Hongru HU, Minda DENG, Yang WANG, Rui MI, Fei WANG, Weichao WANG, Yasheng KWAN, Wai-Chung KING, Irwin WONG, Kam-Fai |
author_sort |
WANG, Hongru |
title |
Large language models as source planner for personalized knowledge-grounded dialogues |
title_short |
Large language models as source planner for personalized knowledge-grounded dialogues |
title_full |
Large language models as source planner for personalized knowledge-grounded dialogues |
title_fullStr |
Large language models as source planner for personalized knowledge-grounded dialogues |
title_full_unstemmed |
Large language models as source planner for personalized knowledge-grounded dialogues |
title_sort |
large language models as source planner for personalized knowledge-grounded dialogues |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2023 |
url |
https://ink.library.smu.edu.sg/sis_research/9121 https://ink.library.smu.edu.sg/context/sis_research/article/10124/viewcontent/2023.findings_emnlp.641.pdf |
_version_ |
1814047747941072896 |