The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Leveraging Fuzzy Fingerprints from Large Language Models for Authorship Attribution
Abstract
Author Attribution has various practical applications such as identifying plagiarism or assigning authorship in historical texts, and plays a crucial role in forensic linguistics. Recent advances have attempted to employ deep learning models for author attribution, resulting in more robust models when compared to previous approaches. In this paper, we introduce a new method to the Author Attribution task and achieve state-of-the-art results in two different datasets. We employ a recent technique that combines Fuzzy Fingerprints with Large Language Models and show that it is possible to obtain unique fingerprints for each author from the datasets. One key feature of this approach is that it allows for a substantial reduction in the size of the output layers of these language models. In addition, we explore the impact of the fingerprint size on the performance of the model and provide illustrative examples of the fingerprints.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Despite this limitation, the researchers achieved 67.4% attribution accuracy on a benchmark involving 50 authors.”
From Generative AI and intellectual property: a systematic literature review of possible issues and mitigations (2026) · cites this paper as Ribeiro, Carvalho & Coheur (2024)
In the citing paper
“A recent study (Ribeiro, Carvalho & Coheur, 2024) proposed an author classification method based on Fuzzy Fingerprints, which are sets of text features (e.g., word patterns) compared using fuzzy logic.”
From Generative AI and intellectual property: a systematic literature review of possible issues and mitigations (2026) · cites this paper as Ribeiro, Carvalho & Coheur, 2024
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
A survey of modern authorship attribution methods
Stamatatos, E. (2009) · Journal of the American Society for Information Science and Technology · doi:10.1002/asi.21001 · Cited by 1,176
Authorship Attribution with Topic Models
Seroussi, Y., Zukerman, I., & Bohnert, F. (2014) · Computational Linguistics · doi:10.1162/coli_a_00173 · Cited by 89
Research works printed but not linked: 29
- 10.1126/science.ns-9.214S.237 · DOI
- 10.1109/NAFIPS.2011.5751998 · DOI
- 10.48550/ARXIV.1907.11692 · DOI · Paper page
- Ribeiro, Fuzzy fingerprinting large pre-trained models, 232
- 10.18653/v1/D18-1294 · DOI
- Sari, Topic or style? exploring the most useful features for authorship attribution, 343
- 10.1063/1.2149832 · DOI
- 10.1109/IRI.2018.00049 · DOI · Paper page
- Bacciu, 2019, Cross-domain authorship attribution combining instance based and profile-based features
- Bagnall, 2015, Author identification using multi-headed recurrent neural networks, arXiv preprint
- 10.1145/3325917.3325935 · DOI
- 10.26615/978-954-452-056-4_062 · DOI
- 10.1109/SMC42975.2020.9283214 · DOI
- 10.1109/TCSS.2021.3067736 · DOI
- 10.1016/j.csl.2021.101241 · DOI
- 10.1007/978-3-030-49161-1_22 · DOI
- Silva, Authorship attribution of late 19th century novels using GAN-BERT, 310
- Fabien, Bertaa: Bert fine-tuning for authorship attribution, 127
- 10.1109/FUZZY.2011.6007446 · DOI
- 10.1109/FUZZ-IEEE.2014.6891781 · DOI
- Rosa, Detecting a tweets topic within a large number of portuguese twitter trends
- 10.1109/FUZZ-IEEE.2018.8491557 · DOI
- 10.1109/FUZZ-IEEE.2016.7737956 · DOI
- 10.1109/FUZZ52849.2023.10309719 · DOI
- Ruder, 2016, Character-level and multi-channel convolutional neural networks for large-scale authorship attribution, arXiv preprint
- 10.1109/ACCESS.2019.2957152 · DOI
- 10.1007/0-387-34224-9_59 · DOI
- 10.18653/v1/E17-2043 · DOI
- 10.1002/asi.22954 · DOI
Cited by
Arnaudo, A., Coppola, R., Morisio, M., Vetrò, A., Borghi, M., Raso, R., & Khan, B. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3928 · Cited by 2
Metadata
- Authors
- Ribeiro, R., Carvalho, J. P., & Coheur, L.
- Affiliations
- INESC-ID, Instituto Superior Técnico, Universidade de Lisboa,Lisbon,Portugal
- Venue
- 2024 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
- Publisher
- IEEE
- Published
- 2024-06-30
- Pages
- 1-7
- Cited by
- 5
- References
- 3
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.
