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

eacl2026-assessing-paper-novelty

Thumbnail Image

Files

data_novelty_assessment.zip (209.42 MB)

Date

2026-01-16

Type

Text

Authors

Mohammed Afzal, Osama
Nakov, Preslav
Hope, Tom
Gurevych, Iryna

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

Dataset for evaluating automated novelty assessment in academic papers. Contains 182 ICLR submissions with human annotations, LLM-derived novelty assessments from reviewer critiques, and system-generated novelty analyses including research landscape overviews and novelty delta comparisons with prior work. This dataset is a supplement to the paper: Beyond "Not Novel Enough": Enriching Scholarly Critique with LLM-Assisted Feedback. Please refer to the paper for more details.

Keywords

Peer Review, AI for Science

Citation

Identifier

https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/4988

Endorsement

DFG Classification

4.43-04 Künstliche Intelligenz und Maschinelle Lernverfahren

Project(s)

Faculty

Collections

License

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