# Embracing Contradiction: Theoretical Inconsistency Will Not Impede the Road of Building Responsible AI Systems

arXiv: https://arxiv.org/abs/2505.18139 · HTML: https://mlsanity.com/paper/2505.18139/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 83 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 30 of 36)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Exploring Generalization in Deep Learning](https://mlsanity.com/paper/1706.08947/) (2017)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [Conflict-Averse Gradient Descent for Multi-task Learning](https://mlsanity.com/paper/2110.14048/) (2021)
- [Scalable agent alignment via reward modeling: a research direction](https://mlsanity.com/paper/1811.07871/) (2018)
- [All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously](https://mlsanity.com/paper/1801.01489/) (2018)
- [Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment](https://mlsanity.com/paper/1610.08452/) (2016)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Improving fairness in machine learning systems: What do industry practitioners need?](https://mlsanity.com/paper/1812.05239/) (2018)
- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [On the Existence of Simpler Machine Learning Models](https://mlsanity.com/paper/1908.01755/) (2019)
- [Exploring the Whole Rashomon Set of Sparse Decision Trees](https://mlsanity.com/paper/2209.08040/) (2022)
- [Amazing Things Come From Having Many Good Models](https://mlsanity.com/paper/2407.04846/) (2024)
- [Empirical observation of negligible fairness-accuracy trade-offs in machine learning for public policy](https://mlsanity.com/paper/2012.02972/) (2020)
- [ToxiCloakCN: Evaluating Robustness of Offensive Language Detection in Chinese with Cloaking Perturbations](https://mlsanity.com/paper/2406.12223/) (2024)
- [Exploring and Interacting with the Set of Good Sparse Generalized Additive Models](https://mlsanity.com/paper/2303.16047/) (2023)
- [Soliciting Stakeholders' Fairness Notions in Child Maltreatment Predictive Systems](https://mlsanity.com/paper/2102.01196/) (2021)
- [The Possibility of Fairness: Revisiting the Impossibility Theorem in Practice](https://mlsanity.com/paper/2302.06347/) (2023)
- [Towards the Right Kind of Fairness in AI](https://mlsanity.com/paper/2102.08453/) (2021)
- [Fairness-Accuracy Trade-Offs: A Causal Perspective](https://mlsanity.com/paper/2405.15443/) (2024)

## Built on by (most cited first, 8 of 8)

- [Hire Your Anthropologist! Rethinking Culture Benchmarks Through an Anthropological Lens](https://mlsanity.com/paper/2510.05931/) (2025)
- [Humanizing Machines: Rethinking LLM Anthropomorphism Through a Multi-Level Framework of Design](https://mlsanity.com/paper/2508.17573/) (2025)
- [Towards Valid Student Simulation with Large Language Models](https://mlsanity.com/paper/2601.05473/) (2026)
- [Epistemic diversity across language models mitigates knowledge collapse](https://mlsanity.com/paper/2512.15011/) (2025)
- [Sentipolis: Emotion-Aware Agents for Social Simulations](https://mlsanity.com/paper/2601.18027/) (2026)
- [Every Act Has Its Price: Compressed Moral Composition in Frontier LLMs](https://mlsanity.com/paper/2606.11232/) (2026)
- [Is your AI Model Accurate Enough? The Difficult Choices Behind Rigorous AI Development and the EU AI Act](https://mlsanity.com/paper/2604.03254/) (2026)
- [An Investigation of the NeurIPS and ICML 2025 Position Tracks](https://mlsanity.com/paper/2608.16894/) (2026)

## Abstract (arXiv)

This position paper argues that the theoretical inconsistency often observed among Responsible AI (RAI) metrics, such as differing fairness definitions or tradeoffs between accuracy and privacy, should be embraced as a valuable feature rather than a flaw to be eliminated. We contend that navigating these inconsistencies, by treating metrics as divergent objectives, yields three key benefits: (1) Normative Pluralism: Maintaining a full suite of potentially contradictory metrics ensures that the diverse moral stances and stakeholder values inherent in RAI are adequately represented. (2) Epistemological Completeness: The use of multiple, sometimes conflicting, metrics allows for a more comprehensive capture of multifaceted ethical concepts, thereby preserving greater informational fidelity about these concepts than any single, simplified definition. (3) Implicit Regularization: Jointly optimizing for theoretically conflicting objectives discourages overfitting to one specific metric, steering models towards solutions with enhanced generalization and robustness under real-world complexities. In contrast, efforts to enforce theoretical consistency by simplifying or pruning metrics risk narrowing this value diversity, losing conceptual depth, and degrading model performance. We therefore advocate for a shift in RAI theory and practice: from getting trapped in inconsistency to characterizing acceptable inconsistency thresholds and elucidating the mechanisms that permit robust, approximated consistency in practice.