@inproceedings{chen-etal-2023-exploring-context,
title = "Exploring In-Context Learning for Knowledge Grounded Dialog Generation",
author = "Chen, Qinyu and
Wu, Wenhao and
Li, Sujian",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.675/",
doi = "10.18653/v1/2023.findings-emnlp.675",
pages = "10071--10081",
abstract = "Large neural-based dialog generation models have been applied in many real-life scenarios, yet they are prone to hallucination and tend to produce factually inaccurate outputs which raise great concerns. To alleviate this problem, we propose a plug-and-play retrieval-based framework IKA, which leverages in-context learning and retrieval techniques to enhance LLMs on knowledge grounded dialog generation. We design thorough experiments on a large-scale knowledge graph with 1M+ facts to investigate the effectiveness and generalization of our framework. Experiments show that our method surpasses previous training-based SOTA by a large margin, specifically 46.67{\%} in BLEU4, 26.01{\%} in ROUGE-L, 122.90{\%} in BARTScore and 30.50{\%} in Entity Coverage F1. Further analysis show promising abilities of LLMs to perform knowledge-intensive tasks, which is previously considered weak and understudied."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2023-exploring-context">
<titleInfo>
<title>Exploring In-Context Learning for Knowledge Grounded Dialog Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qinyu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhao</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large neural-based dialog generation models have been applied in many real-life scenarios, yet they are prone to hallucination and tend to produce factually inaccurate outputs which raise great concerns. To alleviate this problem, we propose a plug-and-play retrieval-based framework IKA, which leverages in-context learning and retrieval techniques to enhance LLMs on knowledge grounded dialog generation. We design thorough experiments on a large-scale knowledge graph with 1M+ facts to investigate the effectiveness and generalization of our framework. Experiments show that our method surpasses previous training-based SOTA by a large margin, specifically 46.67% in BLEU4, 26.01% in ROUGE-L, 122.90% in BARTScore and 30.50% in Entity Coverage F1. Further analysis show promising abilities of LLMs to perform knowledge-intensive tasks, which is previously considered weak and understudied.</abstract>
<identifier type="citekey">chen-etal-2023-exploring-context</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.675</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.675/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>10071</start>
<end>10081</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring In-Context Learning for Knowledge Grounded Dialog Generation
%A Chen, Qinyu
%A Wu, Wenhao
%A Li, Sujian
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F chen-etal-2023-exploring-context
%X Large neural-based dialog generation models have been applied in many real-life scenarios, yet they are prone to hallucination and tend to produce factually inaccurate outputs which raise great concerns. To alleviate this problem, we propose a plug-and-play retrieval-based framework IKA, which leverages in-context learning and retrieval techniques to enhance LLMs on knowledge grounded dialog generation. We design thorough experiments on a large-scale knowledge graph with 1M+ facts to investigate the effectiveness and generalization of our framework. Experiments show that our method surpasses previous training-based SOTA by a large margin, specifically 46.67% in BLEU4, 26.01% in ROUGE-L, 122.90% in BARTScore and 30.50% in Entity Coverage F1. Further analysis show promising abilities of LLMs to perform knowledge-intensive tasks, which is previously considered weak and understudied.
%R 10.18653/v1/2023.findings-emnlp.675
%U https://aclanthology.org/2023.findings-emnlp.675/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.675
%P 10071-10081
Markdown (Informal)
[Exploring In-Context Learning for Knowledge Grounded Dialog Generation](https://aclanthology.org/2023.findings-emnlp.675/) (Chen et al., Findings 2023)
- Exploring In-Context Learning for Knowledge Grounded Dialog Generation (Chen et al., Findings 2023)
ACL
- Qinyu Chen, Wenhao Wu, and Sujian Li. 2023. Exploring In-Context Learning for Knowledge Grounded Dialog Generation. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10071–10081, Singapore. Association for Computational Linguistics.