On Optimal Steering to Achieve Exact Fairness

• URL: http://arxiv.org/abs/2509.15759v1
• Date: Fri, 19 Sep 2025 08:37:51 GMT
• Title: On Optimal Steering to Achieve Exact Fairness
• Authors: Mohit Sharma, Amit Jayant Deshpande, Chiranjib Bhattacharyya, Rajiv Ratn Shah,
• Abstract summary: Empirically, our optimal steering techniques on both synthetic and real-world datasets improve fairness without diminishing utility.<n>We demonstrate affine steering of LLM representations to reduce bias in multi-class classification.
• Score: 29.589891801235083
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To fix the 'bias in, bias out' problem in fair machine learning, it is important to steer feature distributions of data or internal representations of Large Language Models (LLMs) to ideal ones that guarantee group-fair outcomes. Previous work on fair generative models and representation steering could greatly benefit from provable fairness guarantees on the model output. We define a distribution as ideal if the minimizer of any cost-sensitive risk on it is guaranteed to have exact group-fair outcomes (e.g., demographic parity, equal opportunity)-in other words, it has no fairness-utility trade-off. We formulate an optimization program for optimal steering by finding the nearest ideal distribution in KL-divergence, and provide efficient algorithms for it when the underlying distributions come from well-known parametric families (e.g., normal, log-normal). Empirically, our optimal steering techniques on both synthetic and real-world datasets improve fairness without diminishing utility (and sometimes even improve utility). We demonstrate affine steering of LLM representations to reduce bias in multi-class classification, e.g., occupation prediction from a short biography in Bios dataset (De-Arteaga et al.). Furthermore, we steer internal representations of LLMs towards desired outputs so that it works equally well across different groups.

Related papers

• Judging with Confidence: Calibrating Autoraters to Preference Distributions [56.17041629492863]
  We argue that a reliable autorater must learn to model the full distribution of preferences defined by a target population.<n>We present two learning methods tailored to different data conditions.<n>Our results show that finetuning autoraters with a distribution-matching objective leads to verbalized probability predictions that are better aligned with the target preference distribution.
  arXiv  Detail & Related papers  (2025-09-30T20:36:41Z)
• The Statistical Fairness-Accuracy Frontier [50.323024516295725]
  Machine learning models must balance accuracy and fairness, but these goals often conflict.<n>A useful tool for understanding this trade-off is the fairness-accuracy frontier, which characterizes the set of models that cannot be simultaneously improved in both fairness and accuracy.<n>We study the FA frontier in the finite-sample regime, showing how it deviates from its population counterpart and quantifying the worst-case gap between them.
  arXiv  Detail & Related papers  (2025-08-25T03:01:35Z)
• Leveraging Robust Optimization for LLM Alignment under Distribution Shifts [52.983390470606146]
  Preference alignment methods are increasingly critical for steering large language models to generate outputs consistent with human values.<n>We propose a novel distribution-aware optimization framework that improves preference alignment despite such shifts.
  arXiv  Detail & Related papers  (2025-04-08T09:14:38Z)
• FairLoRA: Unpacking Bias Mitigation in Vision Models with Fairness-Driven Low-Rank Adaptation [3.959853359438669]
  We introduce FairLoRA, a novel fairness-specific regularizer for Low Rank Adaptation (LoRA) Our results demonstrate that the need for higher ranks to mitigate bias is not universal; it depends on factors such as the pre-trained model, dataset, and task.
  arXiv  Detail & Related papers  (2024-10-22T18:50:36Z)
• Soft Preference Optimization: Aligning Language Models to Expert Distributions [40.84391304598521]
  SPO is a method for aligning generative models, such as Large Language Models (LLMs), with human preferences. SPO integrates preference loss with a regularization term across the model's entire output distribution. We showcase SPO's methodology, its theoretical foundation, and its comparative advantages in simplicity, computational efficiency, and alignment precision.
  arXiv  Detail & Related papers  (2024-04-30T19:48:55Z)
• Dr. FERMI: A Stochastic Distributionally Robust Fair Empirical Risk Minimization Framework [12.734559823650887]
  In the presence of distribution shifts, fair machine learning models may behave unfairly on test data. Existing algorithms require full access to data and cannot be used when small batches are used. This paper proposes the first distributionally robust fairness framework with convergence guarantees that do not require knowledge of the causal graph.
  arXiv  Detail & Related papers  (2023-09-20T23:25:28Z)
• Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach [72.19525160912943]
  We first theoretically demonstrate the inherent connection between distribution shift, data perturbation, and model weight perturbation. We then analyze the sufficient conditions to guarantee fairness for the target dataset. Motivated by these sufficient conditions, we propose robust fairness regularization (RFR)
  arXiv  Detail & Related papers  (2023-03-06T17:19:23Z)
• Fair and Optimal Classification via Post-Processing [10.163721748735801]
  This paper provides a complete characterization of the inherent tradeoff of demographic parity on classification problems. We show that the minimum error rate achievable by randomized and attribute-aware fair classifiers is given by the optimal value of a Wasserstein-barycenter problem.
  arXiv  Detail & Related papers  (2022-11-03T00:04:04Z)
• Domain Adaptation meets Individual Fairness. And they get along [48.95808607591299]
  We show that algorithmic fairness interventions can help machine learning models overcome distribution shifts. In particular, we show that enforcing suitable notions of individual fairness (IF) can improve the out-of-distribution accuracy of ML models.
  arXiv  Detail & Related papers  (2022-05-01T16:19:55Z)
• Examining and Combating Spurious Features under Distribution Shift [94.31956965507085]
  We define and analyze robust and spurious representations using the information-theoretic concept of minimal sufficient statistics. We prove that even when there is only bias of the input distribution, models can still pick up spurious features from their training data. Inspired by our analysis, we demonstrate that group DRO can fail when groups do not directly account for various spurious correlations.
  arXiv  Detail & Related papers  (2021-06-14T05:39:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.