TU Darmstadt / ULB / TUprints

CiteBench: A Benchmark for Scientific Citation Text Generation

Funkquist, Martin ; Kuznetsov, Ilia ; Hou, Yufang ; Gurevych, Iryna (2024)
CiteBench: A Benchmark for Scientific Citation Text Generation.
The 2023 Conference on Empirical Methods in Natural Language Processing. Singapore (06.-10.12.2023)
doi: 10.26083/tuprints-00027660
Conference or Workshop Item, Secondary publication, Publisher's Version

[img] Text
2023.emnlp-main.455.pdf
Copyright Information: CC BY 4.0 International - Creative Commons, Attribution.

Download (662kB)
[img] Video
2023.emnlp-main.455.mp4
Copyright Information: CC BY 4.0 International - Creative Commons, Attribution.

Download (53MB)
Item Type: Conference or Workshop Item
Type of entry: Secondary publication
Title: CiteBench: A Benchmark for Scientific Citation Text Generation
Language: English
Date: 8 July 2024
Place of Publication: Darmstadt
Year of primary publication: 2023
Place of primary publication: Kerrville, TX, USA
Publisher: ACL
Book Title: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Event Title: The 2023 Conference on Empirical Methods in Natural Language Processing
Event Location: Singapore
Event Dates: 06.-10.12.2023
DOI: 10.26083/tuprints-00027660
Corresponding Links:
Origin: Secondary publication service
Abstract:

Science progresses by building upon the prior body of knowledge documented in scientific publications. The acceleration of research makes it hard to stay up-to-date with the recent developments and to summarize the ever-growing body of prior work. To address this, the task of citation text generation aims to produce accurate textual summaries given a set of papers-to-cite and the citing paper context. Due to otherwise rare explicit anchoring of cited documents in the citing paper, citation text generation provides an excellent opportunity to study how humans aggregate and synthesize textual knowledge from sources. Yet, existing studies are based upon widely diverging task definitions, which makes it hard to study this task systematically. To address this challenge, we propose CiteBench: a benchmark for citation text generation that unifies multiple diverse datasets and enables standardized evaluation of citation text generation models across task designs and domains. Using the new benchmark, we investigate the performance of multiple strong baselines, test their transferability between the datasets, and deliver new insights into the task definition and evaluation to guide future research in citation text generation. We make the code for CiteBench publicly available at https://github.com/UKPLab/citebench.

Identification Number: 2023.emnlp-main.455
Status: Publisher's Version
URN: urn:nbn:de:tuda-tuprints-276602
Classification DDC: 000 Generalities, computers, information > 004 Computer science
Divisions: 20 Department of Computer Science > Ubiquitous Knowledge Processing
Date Deposited: 08 Jul 2024 09:31
Last Modified: 17 Jul 2024 11:52
URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/27660
PPN: 519653335
Export:
Actions (login required)
View Item View Item