@inproceedings{shi-etal-2023-towards,
title = "Towards a Unified Framework for Reference Retrieval and Related Work Generation",
author = "Shi, Zhengliang and
Gao, Shen and
Zhang, Zhen and
Chen, Xiuying and
Chen, Zhumin and
Ren, Pengjie and
Ren, Zhaochun",
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.385",
doi = "10.18653/v1/2023.findings-emnlp.385",
pages = "5785--5799",
abstract = "The task of related work generation aims to generate a comprehensive survey of related research topics automatically, saving time and effort for authors. Existing methods simplify this task by using human-annotated references in a large-scale scientific corpus as information sources, which is time- and cost-intensive. To this end, we propose a Unified Reference Retrieval and Related Work Generation Model (UR3WG), which combines reference retrieval and related work generation processes in a unified framework based on the large language model (LLM). Specifically, UR3WG first leverages the world knowledge of LLM to extend the abstract and generate the query for the subsequent retrieval stage. Then a lexicon-enhanced dense retrieval is proposed to search relevant references, where an importance-aware representation of the lexicon is introduced. We also propose multi-granularity contrastive learning to optimize our retriever. Since this task is not simply summarizing the main points in references, it should analyze the complex relationships and present them logically. We propose an instruction-tuning method to leverage LLM to generate related work. Extensive experiments on two wide-applied datasets demonstrate that our model outperforms the state-of-the-art baselines in both generation and retrieval metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2023-towards">
<titleInfo>
<title>Towards a Unified Framework for Reference Retrieval and Related Work Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhengliang</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shen</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiuying</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhumin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengjie</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaochun</namePart>
<namePart type="family">Ren</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>The task of related work generation aims to generate a comprehensive survey of related research topics automatically, saving time and effort for authors. Existing methods simplify this task by using human-annotated references in a large-scale scientific corpus as information sources, which is time- and cost-intensive. To this end, we propose a Unified Reference Retrieval and Related Work Generation Model (UR3WG), which combines reference retrieval and related work generation processes in a unified framework based on the large language model (LLM). Specifically, UR3WG first leverages the world knowledge of LLM to extend the abstract and generate the query for the subsequent retrieval stage. Then a lexicon-enhanced dense retrieval is proposed to search relevant references, where an importance-aware representation of the lexicon is introduced. We also propose multi-granularity contrastive learning to optimize our retriever. Since this task is not simply summarizing the main points in references, it should analyze the complex relationships and present them logically. We propose an instruction-tuning method to leverage LLM to generate related work. Extensive experiments on two wide-applied datasets demonstrate that our model outperforms the state-of-the-art baselines in both generation and retrieval metrics.</abstract>
<identifier type="citekey">shi-etal-2023-towards</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.385</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.385</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>5785</start>
<end>5799</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards a Unified Framework for Reference Retrieval and Related Work Generation
%A Shi, Zhengliang
%A Gao, Shen
%A Zhang, Zhen
%A Chen, Xiuying
%A Chen, Zhumin
%A Ren, Pengjie
%A Ren, Zhaochun
%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 shi-etal-2023-towards
%X The task of related work generation aims to generate a comprehensive survey of related research topics automatically, saving time and effort for authors. Existing methods simplify this task by using human-annotated references in a large-scale scientific corpus as information sources, which is time- and cost-intensive. To this end, we propose a Unified Reference Retrieval and Related Work Generation Model (UR3WG), which combines reference retrieval and related work generation processes in a unified framework based on the large language model (LLM). Specifically, UR3WG first leverages the world knowledge of LLM to extend the abstract and generate the query for the subsequent retrieval stage. Then a lexicon-enhanced dense retrieval is proposed to search relevant references, where an importance-aware representation of the lexicon is introduced. We also propose multi-granularity contrastive learning to optimize our retriever. Since this task is not simply summarizing the main points in references, it should analyze the complex relationships and present them logically. We propose an instruction-tuning method to leverage LLM to generate related work. Extensive experiments on two wide-applied datasets demonstrate that our model outperforms the state-of-the-art baselines in both generation and retrieval metrics.
%R 10.18653/v1/2023.findings-emnlp.385
%U https://aclanthology.org/2023.findings-emnlp.385
%U https://doi.org/10.18653/v1/2023.findings-emnlp.385
%P 5785-5799
Markdown (Informal)
[Towards a Unified Framework for Reference Retrieval and Related Work Generation](https://aclanthology.org/2023.findings-emnlp.385) (Shi et al., Findings 2023)
ACL