Papers › Parameter-efficient Modularised Bias Mitigation via AdapterFusion

Parameter-efficient Modularised Bias Mitigation via AdapterFusion

13 Feb 2023arXiv:2302.06321archive 2025-07-28

Deepak Kumar, Oleg Lesota, George Zerveas, Daniel Cohen, Carsten Eickhoff, Markus Schedl, Navid Rekabsaz

Large pre-trained language models contain societal biases and carry along these biases to downstream tasks. Current in-processing bias mitigation approaches (like adversarial training) impose debiasing by updating a model's parameters, effectively transferring the model to a new, irreversible debiased state. In this work, we propose a novel approach to develop stand-alone debiasing functionalities separate from the model, which can be integrated into the model on-demand, while keeping the core model untouched. Drawing from the concept of AdapterFusion in multi-task learning, we introduce DAM (Debiasing with Adapter Modules) - a debiasing approach to first encapsulate arbitrary bias mitigation functionalities into separate adapters, and then add them to the model on-demand in order to deliver fairness qualities. We conduct a large set of experiments on three classification tasks with gender, race, and age as protected attributes. Our results show that DAM improves or maintains the effectiveness of bias mitigation, avoids catastrophic forgetting in a multi-attribute scenario, and maintains on-par task performance, while granting parameter-efficiency and easy switching between the original and debiased models.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

cpjku/modularizeddebiasing officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

AttributeFairnessMulti-Task Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Adapter

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections