Adversarial Debiasing

Latest papers

8 papers3 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Bias Mitigation in Audio-Enabled LLMs through Adversarial Training and Distillation Methods
Oct 15, 2026Adnan Al Ali, Jindřich Libovický, Anne LauscherAdversarial Debiasing Language Model Debiasing
Charles University, Faculty of Mathematics and Physics, Czech Republic · Trustworthy AI Lab, University of Hamburg, Germany
Who Wrote It Is Not Enough: Detecting Who Contributed the Insight
Oct 5, 2026Zhuoyang Zou, Abolfazl Ansari, Jiaxi Yang +4Data Provenance Scholarly Peer Review
Pennsylvania State University, USA · University of Sheffield, United Kingdom
Adversarial Debiasing of Machine Learning Models for Enhanced Network Security against DDoS Attacks
Sep 28, 2026Aadith Sukumar, Isha Singh, Devershika Mohane +4Network Intrusion Detection Adversarial Debiasing
Symbiosis Institute of Technology Pune, India · Symbiosis Center for Applied Artificial Intelligence, Pune, India · Peoples’ Friendship University of Russia Moscow, Russian Federation
Evaluating and Mitigating Gender Bias in Pre-trained Embeddings for ML-based Recruitment
Jul 22, 2026Farnaz Faramarzi Lighvan, Lynn HouthuysGender Bias in Language Models Algorithmic Fairness
AI Lab, Vrije Universiteit Brussel, Belgium
Causal-Adversarial Probing of Clinical Covariates for Prostate MRI Grading
Jul 16, 2026Yipei Wang, Shiqi Huang, Wen Yan +6Causal Representation Learning Medical Image Classification
UCL Hawkes Institute, University College London, London, UK · Department of Medical Physics and Biomedical Engineering, University College London, London, UK · Department of Urology, University College London Hospital, London, UK +4
Effect of Demographic Bias on Skin Lesion Classification
Jun 2, 2026Ralf Raumanns, Gerard Schouten, Veronika Cheplygina +1Skin Lesion Classification Algorithmic Bias
Fontys University of Applied Science, Venlo, The Netherlands · Eindhoven University of Technology, Eindhoven, The Netherlands · IT University of Copenhagen, Denmark +1
Combating Pattern and Content Bias: Adversarial Feature Learning for Generalized AI-Generated Image Detection
Apr 14, 2026Haifeng Zhang, Qinghui He, Xiuli Bi +3Adversarial Debiasing AI-Generated Image Detection
Chongqing Key Laboratory of Image Cognition, School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China · School of Artificial Intelligence, Chongging Key Laboratory of Image Cognition, Chongging University of Posts and Telecommunications, Chongqing 400065, China · Faculty of Science and Technology of the University of Macau, Macau 999078, China +1
Mitigating Bias in Concept Bottleneck Models for Fair and Interpretable Image Classification
Mar 6, 2026Schrasing Tong, Antoine Salaun, Vincent Yuan +2Adversarial Debiasing Concept Bottleneck Models
Massachusetts Institute of Technology, United States

Oct 15, 2026J/K move · Enter open · S save

Bias Mitigation in Audio-Enabled LLMs through Adversarial Training and Distillation Methods

Adnan Al Ali, Jindřich Libovický, Anne Lauscher

Charles University, Faculty of Mathematics and Physics, Czech Republic · Trustworthy AI Lab, University of Hamburg, Germany

Adversarial Debiasing Language Model Debiasing Gender Bias in Language Models Audio-Language Models LLM Unlearning Adversarial Training+1

Open paper AskPDF arXiv

Audio-enabled large language models (AuLLMs) allow users to interact with them simply by talking to them, without the need for an intermediate transcription. This expands the model's accessibility and capabilities by encoding non-verbal cues. However, using non-verbal cues may lead to biased behaviour based on the attributes inferred (or assumed) from them. In this work, we focus on the gender attribute and show that models' perception of it can be unlearned using adversarial methods without a loss in performance on other benchmarked tasks. Such models are useful in situations where gender inference is unwanted. However, in other practical settings, gender perception (without bias) may be desired.As a less radical measure, we distil the gender-agnostic model, creating a model that perceives gender but responds similarly to the gender-agnostic teacher, unless explicitly asked.We apply our newly proposed methods to three AuLLMs and obtain satisfactory results in the gender-unlearning part and partially satisfactory results in the distilling part.