# The Trade-off between Performance, Efficiency, and Fairness in Adapter Modules for Text Classification

arXiv: https://arxiv.org/abs/2405.02010 · HTML: https://mlsanity.com/paper/2405.02010/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 3 May 2024.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [AdapterHub: A Framework for Adapting Transformers](https://mlsanity.com/paper/2007.07779/) (2020)
- [Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting](https://mlsanity.com/paper/1901.09451/) (2019)
- [Simple, Scalable Adaptation for Neural Machine Translation](https://mlsanity.com/paper/1909.08478/) (2019)
- [AdapterDrop: On the Efficiency of Adapters in Transformers](https://mlsanity.com/paper/2010.11918/) (2020)
- [Sustainable Modular Debiasing of Language Models](https://mlsanity.com/paper/2109.03646/) (2021)
- [Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models](https://mlsanity.com/paper/2202.04173/) (2022)
- [Your fairness may vary: Pretrained language model fairness in toxic text classification](https://mlsanity.com/paper/2108.01250/) (2021)
- [Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Bias](https://mlsanity.com/paper/2206.09860/) (2022)
- [Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold](https://mlsanity.com/paper/2206.09755/) (2022)
- [Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation](https://mlsanity.com/paper/2106.00169/) (2021)
- [Parameter-efficient Modularised Bias Mitigation via AdapterFusion](https://mlsanity.com/paper/2302.06321/) (2023)

## Built on by (most cited first, 2 of 2)

- [3DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selection](https://mlsanity.com/paper/2410.10901/) (2024)
- [From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop](https://mlsanity.com/paper/2608.11171/) (2026)

## Abstract (arXiv)

Current natural language processing (NLP) research tends to focus on only one or, less frequently, two dimensions - e.g., performance, privacy, fairness, or efficiency - at a time, which may lead to suboptimal conclusions and often overlooking the broader goal of achieving trustworthy NLP. Work on adapter modules (Houlsby et al., 2019; Hu et al., 2021) focuses on improving performance and efficiency, with no investigation of unintended consequences on other aspects such as fairness. To address this gap, we conduct experiments on three text classification datasets by either (1) finetuning all parameters or (2) using adapter modules. Regarding performance and efficiency, we confirm prior findings that the accuracy of adapter-enhanced models is roughly on par with that of fully finetuned models, while training time is substantially reduced. Regarding fairness, we show that adapter modules result in mixed fairness across sensitive groups. Further investigation reveals that, when the standard fine-tuned model exhibits limited biases, adapter modules typically do not introduce extra bias. On the other hand, when the finetuned model exhibits increased bias, the impact of adapter modules on bias becomes more unpredictable, introducing the risk of significantly magnifying these biases for certain groups. Our findings highlight the need for a case-by-case evaluation rather than a one-size-fits-all judgment.