Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering

Targeted bias injection via closed-loop activation steering exploits diffusion language model denoising trajectories to steer frozen models toward adversarial demographic answers with minimal corruption.

Sarim Hashmi, Mukul Ranjan, Abdelrahman Elsayed, Muhammad Umer Sheikh and 2 more

Published Oct 5, 2026 · ▲ 14 on Hugging Face · Code ★ 3

FairRSFM: A Biome-Aware Benchmark and Debiasing Framework for Remote Sensing Foundation Models

FairRSFM benchmarks remote sensing foundation models by biome to expose hidden ecological performance disparities and tests debiasing methods without backbone updates. Aggregate metrics consistently mask large biome-dependent gaps, though mitigation effectiveness varies by model and task.

Md Aminur Hossain, Omkumar Vaghasiya, Rajeev Ranjan Dwivedi, Vinod Kurmi and 1 more

Published Oct 5, 2026 · ▲ 5 on Hugging Face · Code

Collective Bias Mitigation via Model Routing and Collaboration

Collective Bias Mitigation routes queries among diverse LLMs and fosters collaboration to substantially reduce bias over single-model baselines.

Mingzhe Du, Luu Anh Tuan, Xiaobao Wu, Yichong Huang and 6 more

Published Oct 2, 2026 · 0 citations · ▲ 14 on Hugging Face

Adversarial Attacks on Fairness of Graph Neural Networks

G-FairAttack is a framework that adversarially corrupts fairness in fairness-aware graph neural networks while preserving prediction utility.

Binchi Zhang, Yushun Dong, Chen Chen, Yada Zhu and 2 more

Published Oct 20, 2023 · 1 citation · ▲ 1 on Hugging Face · Code ★ 11

From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models

Pretraining data political biases propagate through language models into unfair hate speech and misinformation detectors, reinforcing polarization.

Shangbin Feng, Chan Young Park, Yuhan Liu, Yulia Tsvetkov

Published 2023 · 138 citations

TailGuard: Subgroup Tail Coverage Theory for Safe LLM Alignment

Charles Cao

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Distributionally Robust Algorithmic Recourse for Tree Ensembles

Kentaro Kanamori, Ken Kobayashi, Takuya Takagi

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Compact Representations of Impact-Based Fair-Ranking Policies

Yuki Uehara, Naoki Nishimura, Noriyoshi Sukegawa, Yuichi Takano

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Multigroup Fairness and Omniprediction: Separations and Equivalences

Sílvia Casacuberta, Parikshit Gopalan, Varun Kanade, Omer Reingold and 2 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Text-Based AI Tools for Research Integrity Must Be Audited on Linguistic Fairness Before Deployment

Shuai Shao, Yongkang Wan, Daoyin Dang, Lanyun Zhu and 4 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

The Pok\'emon Theorem and other Fairness Impossibility Results

Daniel Matsui Smola, Alexander Smola

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

An Information-theoretic Framework for Auditing Unfairness in Training Data

Mohamed Nafea, Sokrat Aldarmini

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Treat Bias as Noise: Training Bias-Robust LLM Reasoning via Reinforcement Learning

Qian Wang, Xuandong Zhao, Zirui Zhang, Zhanzhi Lou and 3 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

CultureRed: Benchmarking Culture-Specific AI Safety Based on Global Statutes

Xun Liu, Mintong Kang, Seok Min Lim, Ong C Hui and 1 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

New Coresets for Fair Clustering

Xuan Wu, Chansophea Wathanak In, Yi Li

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

On the Bias of Group-Based Advantage Estimation

Fengkai Yang, Zherui Chen, Xiaohan Wang, Xiaodong Lu and 8 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

Overcoming the Resolution Limit: Significance-Aware Regularization for Intersectional Fairness

Antonio Ferrara, André Panisson, Francesco Cozzi, Alan Perotti and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Malicious Node Injection: A Transferable Adversarial Attack on GNN Fairness

Haotian Zhang, He Huang, Shuang Cui, Yu-e Sun

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Practical Estimation of the Bayes Optimal Fairness-Accuracy Tradeoff with Soft Labels

mohit sharma, Okan Koc, Amit Jayant Deshpande, Takashi Ishida and 3 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

FedCF: Fair Federated Conformal Prediction

Anutam Srinivasan, Aditya T. Vadlamani, Amin Meghrazi, Srinivasan Parthasarathy

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Elicited Adaptation: Auditable Localized Fairness via Pairwise Queries

Shrey Shah

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Adversarial Group Fairness in Contextual Bandits: When Robust is Not Fair

Ray Telikani, Jaber valizadeh, Amir H Gandomi, Bao Q Vo and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Position: Fair Representations Cannot Hold What They Promise

Shai Ben-David, Tosca Lechner, Ruth Urner

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

Characterizing Underrepresentation in Generalizing Causal Survival Estimates

Bolun Liu, Sean McGrath, Yiren Hou, Elizabeth Stuart and 1 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Fairness in limited resource prediction-driven decisions

Inbal Livni Navon, Eitan Bachmat

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

Jointly Robust Fairness: Overcoming Simultaneous Label and Attribute Noise

Gaurav Jain

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Simultaneous Individual, Group and Multigroup Fairness in Set Covering Problems

Sharmila Duppala, Nathaniel Grammel, Tyler He, Aravind Srinivasan

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

A Simple Class-Agnostic Approach to Enhance Fair Adversarial Training

Erh-Chung Chen, Pin-Yu Chen, I-Hsin Chung, Che-Rung Lee

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

KINDER: Kernel-based Independence for Fair Representation Learning via Prototype-space Erasure

Abtin Mogharabin, Jiaee Cheong, Alp Toykan Kaplan, Sinan Kalkan

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

Towards Fairness under Label Bias in Image Segmentation: Impact, Measurement and Mitigation

A confident learning framework audits segmentation label bias without unbiased ground truth and mitigates subgroup disparities via feature-space separability.

Aditya Parikh, Stella Christina Frank, Sneha Das, Aasa Feragen

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales

StayFair decomposes diffusion bias into model and guidance components, deriving a guidance-scale-invariant fairness condition and algorithms that maintain group fairness across all guidance scales without quality loss.

Myeongsoo Kim, Eunji Kim, Minwoo Chae, Sangwoo Mo

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Controlling for Omitted Variable Bias in Deep Neural Networks

A control-variable method using generalized additive modeling and cross-fitted ridge refitting removes omitted-variable bias from deep networks, yielding unbiased predictions.

Manuel Pfeuffer, Roshan P Rane, Kerstin Ritter, Sonja Greven

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

Efficient bias mitigation in T2I diffusion models using Concept Graphs

CO-ALIGN reduces text-to-image diffusion bias via concept-graph alignment across encoders and denoisers, cutting incoherent outputs by 88% while improving fairness and fidelity.

Mansi -, Avinash Kori, Francesco Leofante

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

FairMT: Fairness for Heterogeneous Multi-Task Learning

FairMT introduces a unified fairness framework for heterogeneous multi-task learning with partial labels, using asymmetric constraint aggregation and head-aware optimization to improve fairness without sacrificing utility.

Guanyu Hu, Tangzheng Lian, Na Yan, Dimitrios Kollias and 4 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

A Comprehensive View of Fairness through Distributional Stability

Reframing fairness as distributional stability under protected-group shifts unifies classical fairness notions via Lipschitz constants and yields a second-order cone program with uniform test-time guarantees.

Gayane Taturyan, Charlotte Laclau, Stephan Clémençon

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

Mitigating Label Bias with Interpretable Rubric Embeddings

Rubric embeddings replace black-box features with expert-defined criteria to reduce label bias, cutting group disparities and improving cohort quality in admissions predictions.

Calvin Isley, Johann D. Gaebler, Sharad Goel

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Accuracy vs. Accuracy: Computational Tradeoffs Between Classification Rates and Utility

Algorithms preserve accurate subpopulation classification rates and enable loss minimization, but simultaneously achieving both is computationally infeasible despite Bayes-optimal feasibility.

Noga Amit, Omer Reingold, Guy Rothblum

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Geometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware Settings

Optimal transport characterizes relaxed fair regression via smooth population-wide or exact subset parity penalties across aware and unaware settings, and proposed algorithms match or exceed state-of-the-art benchmarks.

Marie Generali Lince, Vincent Divol, Rémi Flamary, Solenne Gaucher and 1 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

On the Burden of Achieving Fairness in Conformal Prediction

Pooled conformal calibration causes irreducible cross-group coverage distortion and a fundamental tension between equalized coverage and set size. Calibration shifts heterogeneity between coverage and size rather than removing it.

Ziang Gao, Pengqi Liu, Archer Yang, Mouloud Belbahri and 2 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face

Rank-Constrained Adaptation for Reliable Real-World Performance

MARLA improves worst-group accuracy without subgroup labels by applying a rank-limited logit correction within a low-dimensional misclassification subspace identified from held-out data.

Abinitha Gourabathina, Hyewon Jeong, Teya Bergamaschi, Marzyeh Ghassemi and 1 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Intersectional Fairness via Mixed-Integer Optimization

A mixed-integer optimization framework trains interpretable classifiers that bound intersectional bias below acceptable thresholds across protected subgroups.

Jiří; Němeček, Mark Kozdoba, Illia Kryvoviaz, Tomáš Pevný and 1 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs

StereoTales reveals open-ended LLM generation emits shared harmful stereotypes that culturally adapt to prompt languages and align with human harmfulness ratings.

Pierre Le Jeune, Etienne Duchesne, Weixuan Xiao, Stefano Palminteri and 3 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

Scalable Fair Learning via Cramér-von Mises Regularization

A Cramér-von Mises fairness regularizer with O(B log B) complexity penalizes prediction-sensitive attribute dependence during training, achieving competitive fairness-utility trade-offs with lower overhead.

Albert Gimó Contreras, Mariia Vladimirova, Olga Petrova, Reda CHHAIBI and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026