mlsanityData to 7 Oct 2026

Quantifying Misattribution Unfairness in Authorship Attribution

arXiv 2506.02321 ↗First posted 2 Jun 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Authorship misattribution can have profound consequences in real life. In forensic settings simply being considered as one of the potential authors of an evidential piece of text or communication can result in undesirable scrutiny. This raises a fairness question: Is every author in the candidate pool at equal risk of misattribution? Standard evaluation measures for authorship attribution systems do not explicitly account for this notion of fairness. We introduce a simple measure, Misattribution Unfairness Index (MAUIk), which is based on how often authors are ranked in the top k for texts they did not write. Using this measure we quantify the unfairness of five models on two different datasets. All models exhibit high levels of unfairness with increased risks for some authors. Furthermore, we find that this unfairness relates to how the models embed the authors as vectors in the latent search space. In particular, we observe that the risk of misattribution is higher for authors closer to the centroid (or center) of the embedded authors in the haystack. These results indicate the potential for harm and the need for communicating with and calibrating end users on misattribution risk when building and providing such models for downstream use.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 40 references that are in the map. First posted on arXiv 2 Jun 2025.

Builds on

21 of 40 references.

References · 21

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  4. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 973
  5. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  6. 2018Equity of Attention: Amortizing Individual Fairness in Rankingscited by 124
  7. 2019Does Gender Matter? Towards Fairness in Dialogue Systemscited by 89
  8. 2021Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metricscited by 83
  9. 2022Same Author or Just Same Topic? Towards Content-Independent Style Representationscited by 83
  10. 2016Measuring Fairness in Ranked Outputscited by 81
  11. 2022On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representationscited by 75
  12. 2024Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challengescited by 46
9 more
  1. 2024StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examplescited by 32
  2. 2022On the State of the Art in Authorship Attribution and Authorship Verificationcited by 27
  3. 2021A Deep Metric Learning Approach to Account Linkingcited by 24
  4. 2019Learning Invariant Representations of Social Media Userscited by 21
  5. 2021Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classificationcited by 20
  6. 2021Maxmin-Fair Ranking: Individual Fairness under Group-Fairness Constraintscited by 18
  7. 2023Can Authorship Representation Learning Capture Stylistic Features?cited by 17
  8. 2024Do Large Language Models Rank Fairly? An Empirical Study on the Fairness of LLMs as Rankerscited by 17
  9. 2020Overview of the TREC 2019 Fair Ranking Trackcited by 4

Built on by

Not cited yet.