# Quantifying Misattribution Unfairness in Authorship Attribution

arXiv: https://arxiv.org/abs/2506.02321 · HTML: https://mlsanity.com/paper/2506.02321/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 21 of 21)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Equity of Attention: Amortizing Individual Fairness in Rankings](https://mlsanity.com/paper/1805.01788/) (2018)
- [Does Gender Matter? Towards Fairness in Dialogue Systems](https://mlsanity.com/paper/1910.10486/) (2019)
- [Same Author or Just Same Topic? Towards Content-Independent Style Representations](https://mlsanity.com/paper/2204.04907/) (2022)
- [Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics](https://mlsanity.com/paper/2106.14574/) (2021)
- [Measuring Fairness in Ranked Outputs](https://mlsanity.com/paper/1610.08559/) (2016)
- [On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations](https://mlsanity.com/paper/2203.13928/) (2022)
- [Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges](https://mlsanity.com/paper/2408.08946/) (2024)
- [StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples](https://mlsanity.com/paper/2410.12757/) (2024)
- [On the State of the Art in Authorship Attribution and Authorship Verification](https://mlsanity.com/paper/2209.06869/) (2022)
- [A Deep Metric Learning Approach to Account Linking](https://mlsanity.com/paper/2105.07263/) (2021)
- [Learning Invariant Representations of Social Media Users](https://mlsanity.com/paper/1910.04979/) (2019)
- [Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification](https://mlsanity.com/paper/2106.10826/) (2021)
- [Maxmin-Fair Ranking: Individual Fairness under Group-Fairness Constraints](https://mlsanity.com/paper/2106.08652/) (2021)
- [Can Authorship Representation Learning Capture Stylistic Features?](https://mlsanity.com/paper/2308.11490/) (2023)
- [Do Large Language Models Rank Fairly? An Empirical Study on the Fairness of LLMs as Rankers](https://mlsanity.com/paper/2404.03192/) (2024)
- [Overview of the TREC 2019 Fair Ranking Track](https://mlsanity.com/paper/2003.11650/) (2020)

## 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.