Der Login über E-Mail und Passwort wird in Kürze abgeschaltet. Für Externe steht ab sofort der Login über ORCID zur Verfügung.
The login via e-mail and password will be retired in the near future. External uses can login via ORCID from now on.
 
Open Access

Attribute or Abstain: Large Language Models as Long Document Assistants

Thumbnail Image

Files

code.zip (The code as found on github on 30 Oct 2024 (commit 5f33637)) (2.17 MB)
 data.zip (Datasets and basic data directory structure.) (1.31 GB)

Date

2024-10-16

Type

Text

Authors

Buchmann, Jan
Liu, Xiao
Gurevych, Iryna

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

This folder contains data to run experiments on LAB, the Long document Attribution Benchmark introduced in "Attribute or Abstain: Large Language Models as Long Document Assistants". All datasets were converted to the Intertext Graph format introduced by Kuznetsov et al. (2022).

Keywords

long document, intertext, attribution, qasper, natural questions, evidence inference, wice, contractnli, govreport

Citation

Identifier

https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/4276.4

Endorsement

Related Resources

Is Supplement To
https://github.com/UKPLab/arxiv2024-attribute-or-abstain

DFG Classification

4.43-04 Künstliche Intelligenz und Maschinelle Lernverfahren
4.43-05 Bild- und Sprachverarbeitung, Computergraphik und Visualisierung, Human Computer Interaction, Ubiquitous und Wearable Computing

Project(s)

EC/HE | 101054961 | InterText

Faculty

Collections

License

CC BY 4.0 - Attribution 4.0 International
Except where otherwise noted, this license is described as CC BY 4.0 - Attribution 4.0 International

Version History

Now showing 1 - 3 of 3
VersionDateSummary
4*
 2024-10-16 10:37:39
Uploaded zip file was faulty.
2
 2024-06-27 12:46:28
Add acknowledgement
1
 2024-06-27 12:44:05
* Selected version