Debiased ML

ML: Machine Learning

Ask about this topic

Overview

Debiased machine learning addresses both unfair or shortcut-driven predictions and bias in statistical estimates of causal effects or other target quantities. Fairness and robustness methods include counterfactual constraints, group-aware reweighting, representation or neuron interventions, and data selection, with applications to language models, image classifiers, reward models, and generative systems. For statistical estimation, double/debiased machine learning uses cross-fitting, Neyman-orthogonal scores, and Riesz regression to limit the effect of errors in nuisance models. A central challenge is to verify that measured fairness reflects genuine correction rather than reduced confidence or shifted harms, while preserving accuracy and reliable inference across groups and settings.

Latest papers

CardsList

56 papers8 papers in the last four weeks, up 167% on the four weeks before. 0.0% of all new papers.

  1. When Is a Cheap Fairness Edit Safe? Screening Post-Hoc Edits in Two-Sided Matching Markets

    Oct 27, 2026Moirangthem Tiken Singha, Rabinder Kumar PrasadaFair Resource AllocationDebiased ML

    Department of Computer Science and Engineering, Dibrugarh University Institute of Engineering and Technology, Dibrugarh University, Dibrugarh, Assam, India

  2. Rethinking Post-hoc Debiasing of Large Pretrained Models

    Oct 21, 2026Divyaansh Mertia, Chirag Bhutra, Himanshu Shekhar +2Debiased MLLanguage Model Debiasing

    Indian Institute of Technology Jodhpur

  3. Trajectory-Guided Steering: Mitigating Spurious Feature Bias in Clinical Classification

    Oct 15, 2026Fardin Ahsan Sakib, Ziwei Zhu, Ozlem UzunerDebiased MLLanguage Model Steering

    Department of Computer Science, George Mason University · Department of Information Sciences and Technology, George Mason University

  4. Latent space bias directions in LLMs capture confidence, not fairness

    Oct 6, 2026Stephanie Buttigieg, Maeve Madigan, Parameswaran Kamalaruban +1Debiased MLLanguage Model Steering

    Institute of Astronomy & Kavli Institute for Cosmology, University of Cambridge, UK · Risk and Security AI Lab, Visa Inc., Cambridge, UK

  5. BiasFlow: Geometric Monitoring and Backbone Regularization for Spurious Feature Reliance

    Oct 5, 2026Haojin Deng, Zhiping Lin, Yimin YangDebiased MLSpurious Correlation Robustness

    Vector Institute, Toronto, Canada

  6. Causal Lag Structure Discovery in Confounded Time Series via Orthogonalized Adaptive Estimation

    Oct 4, 2026Hong Kiat Tan, Isaac-Neil Zanoria, James Chen +2Debiased MLTime-Series Causal Discovery

    Department of Mathematics, University of California, Los Angeles · Department of Electrical and Computer Engineering, University of California, Los Angeles · Oxford-Man Institute of Quantitative Finance, University of Oxford +1

  7. Debias Anything: Fairness with Diversity without Supervision in Diffusion Models

    Oct 1, 2026Théau d'Audiffret, Mariia Vladimirova, Jean-Yves FranceschiDiffusion Model GuidanceDebiased ML

    Criteo AI Lab, Paris, France · ESSEC Business School, France · CentraleSupélec, Université Paris-Saclay, France +1

  8. Acmite: Mitigating Gender Bias in LLMs through Concept-Guided Mutual Information

    Oct 1, 2026Tian Lan, Xiaoqing Cheng, Han Zhang +1Gender Bias in Language ModelsDebiased ML

    Kyoto University · Zhejiang University · Shanghai Jiao Tong University +1

  9. BA-DPO: Bias-Adjusted Direct Preference Optimization for Language Model Alignment

    Sep 28, 2026Antonio Ferrara, Alberto Rumi, Francesco BonchiLLM AlignmentDebiased ML

    Intesa Sanpaolo AI Research

  10. Integrating Fairness and Explainability in a Multiple Instance Reinforcement Learning System

    Sep 2, 2026Bente Hinkenhuis, Seyed Sahand Mohammadi Ziabari, Ali Mohammed Mansoor AlsahagAlgorithmic FairnessDebiased ML

    University of Amsterdam Amsterdam, The Netherlands

  11. Debias-SparseGPT: Bias-Aware Pruning for Large Language Models

    Sep 2, 2026Irina Proskurina, Guillaume Metzler, Antoine Gourru +1LLM PruningNeural Network Pruning

    1Laboratoire Hubert Curien, UMR CNRS 5516, Saint-Étienne, France · 2Université Claude Bernard Lyon 1, Université Lumière Lyon 2, ERIC · 3École Centrale de Lyon, LIRIS, CNRS UMR 5205

  12. Patterning in Practice: Debiasing Reward Models with Susceptibilities

    Sep 1, 2026George Wang, Elizabeth Donoway, Daniel MurfetReward ModelingDebiased ML

    Resolution

  13. When Prediction Error Is Not Enough: Evaluating Nuisance-Function Prediction for Causal Estimation

    Aug 30, 2026Cong CaoSemiparametric InferenceCausal Effect Estimation

    Department of Biostatistics, Yale University, New Haven, CT 06520, USA

  14. Controlling for Omitted Variable Bias in Deep Neural Networks

    Aug 26, 2026Manuel Pfeuffer, Roshan Prakash Rane, Kerstin Ritter +1Debiased MLShortcut Learning

    Humboldt-Universität zu Berlin, Berlin, Germany · Hertie Institute for AI in Brain Health, Universität Tübingen, Tübingen, Germany · Universität Tübingen, Tübingen, Germany

  15. When Debiasing Backfires: Counterintuitive Side Effects of Preprocessing-Based Stereotype Mitigation

    Jul 8, 2026Yahan Zheng, John Guerrerio, Soroush Vosoughi +1Debiased MLSocial Bias in Language Models

    Dartmouth College · Oakland University

  16. Selective Test-Time Debiasing for CLIP via Reward Gating

    Jul 1, 2026Jaeho Han, Jisoo Yang, Hyeondong Woo +3Debiased MLVLM Adaptation

    Department of Artificial Intelligence, Chung-Ang University

  17. Estimating Supply Incrementality in Two-sided Marketplaces: A Causal Machine Learning Approach

    Jun 30, 2026Yufei Wu, Daniel Schmierer, Dan ZylberglejdCausal Effect EstimationDebiased ML

    Airbnb, Inc. San Francisco, California, USA

  18. CouCE: A Unified Causal Framework for Debiased Deep Metric Learning

    Jun 29, 2026Xin Yuan, Zhenyang Niu, Meiqi Wan +3Debiased MLCausal Representation Learning

    Wuhan University of Science and Technology Wuhan, China · Harbin Institute of Technology Harbin, China

  19. Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement

    Jun 23, 2026Xiangqian Zhao, Xinyang Jiang, Zhipeng Xu +5Disentangled Representation LearningDebiased ML

    Xidian University · Shaanxi, China · Microsoft Research Asia +1

  20. Data Bias Mitigation under Coverage Constraints & The Price of Fairness

    Jun 18, 2026Bruno Scarone, Alfredo Viola, Renée J. MillerDebiased MLAlgorithmic Fairness

    Khoury College of Computer Sciences, Northeastern University, USA · Casa de Investigadores Científicos La Comarca, Uruguay · Cheriton School of Computer Science, University of Waterloo, Canada

  21. Identification and Inference for Algorithmic Frontiers with Selective Labels

    Jun 12, 2026Yiqi Liu, Francesca Molinari, Amilcar VelezDebiased MLParameter Identifiability

    Department of Economics, Cornell University

  22. Prediction-Powered Causal Inference by Automatic Debiased Machine Learning and Semi-Supervised Riesz Regression

    Jun 11, 2026Masahiro KatoSemiparametric InferenceParameter Estimation

    Data Analytics Department, Mizuho-DL Financial Technology, Co., Ltd.

  23. Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles

    Jun 10, 2026Shun Shao, Zheng Zhao, Anna Korhonen +2Debiased MLAlgorithmic Fairness

    University of Cambridge · University of Edinburgh · University of Groningen +1

  24. Detecting and Mitigating Bias by Treating Fairness as a Symmetry Operation

    Jun 2, 2026Nishit SinghDebiased MLAlgorithmic Fairness

    Birla Institute of Technology and Science, Pilani.

  25. Mitigating Spurious Correlations with Memorization-Guided Dataset De-Biasing

    Jun 1, 2026Arda Fazla, Abolfazl HashemiDebiased MLTraining Data Selection

    School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA.

  26. Bias Leaves a Gradient Trail: Label-Free Bias Identification via Gradient Probes on Concept Decompositions

    May 27, 2026Thomas Vitry, Kieran Edgeworth, Stefan Wermter +1Debiased MLSpurious Correlation Robustness

    University of Hamburg, Hamburg, Germany · Ecole Normale Superieure de Rennes, Rennes, France

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

    May 27, 2026Myeongsoo Kim, Eunji Kim, Minwoo Chae +1Diffusion Model GuidanceClassifier-Free Guidance

    POSTECH · Amazon

  28. DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation

    May 15, 2026Rui Chu, Bingyin Zhao, Thanh Quoc Hung Le +6Retrieval-Augmented GenerationDebiased ML

  29. Covariate Balancing and Riesz Regression Should Be Guided by the Neyman Orthogonal Score in Debiased Machine Learning

    May 7, 2026Masahiro KatoCausal Effect EstimationDebiased ML

    Data Analytics Department, Mizuho-DL Financial Technology, Co., Ltd.

  30. Decoding-Time Debiasing via Process Reward Models: From Controlled Fill-in to Open-Ended Generation

    May 4, 2026Muneeb Ur Raheem KhanSocial Bias in Language ModelsLanguage Model Decoding

    Lahore University of Management Sciences (LUMS)