# Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution

arXiv: https://arxiv.org/abs/2605.02640 · HTML: https://mlsanity.com/paper/2605.02640/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 90 references that are in the map.
- First posted on arXiv 4 May 2026.

## Builds on (most cited first, 30 of 51)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [The Risks of Invariant Risk Minimization](https://mlsanity.com/paper/2010.05761/) (2020)
- [Algorithmic Recourse: from Counterfactual Explanations to Interventions](https://mlsanity.com/paper/2002.06278/) (2020)
- [Measuring and Reducing Gendered Correlations in Pre-trained Models](https://mlsanity.com/paper/2010.06032/) (2020)
- [Attribution Patching Outperforms Automated Circuit Discovery](https://mlsanity.com/paper/2310.10348/) (2023)
- [Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability](https://mlsanity.com/paper/2301.04709/) (2023)
- [Avoiding Discrimination through Causal Reasoning](https://mlsanity.com/paper/1706.02744/) (2017)
- [Path-Specific Counterfactual Fairness](https://mlsanity.com/paper/1802.08139/) (2018)
- [Inherent Tradeoffs in Learning Fair Representations](https://mlsanity.com/paper/1906.08386/) (2019)
- [The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4](https://mlsanity.com/paper/2311.07361/) (2023)
- [Causal Machine Learning: A Survey and Open Problems](https://mlsanity.com/paper/2206.15475/) (2022)
- [Debiasing Pre-trained Contextualised Embeddings](https://mlsanity.com/paper/2101.09523/) (2021)
- [Robust agents learn causal world models](https://mlsanity.com/paper/2402.10877/) (2024)
- [On the Origins of Linear Representations in Large Language Models](https://mlsanity.com/paper/2403.03867/) (2024)
- [Identifying Spurious Correlations for Robust Text Classification](https://mlsanity.com/paper/2010.02458/) (2020)
- [Fair Decision Making using Privacy-Protected Data](https://mlsanity.com/paper/1905.12744/) (2019)
- [Causal Reasoning for Algorithmic Fairness](https://mlsanity.com/paper/1805.05859/) (2018)
- [A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task](https://mlsanity.com/paper/2402.11917/) (2024)
- [On the relation between accuracy and fairness in binary classification](https://mlsanity.com/paper/1505.05723/) (2015)
- [A fast PC algorithm for high dimensional causal discovery with multi-core PCs](https://mlsanity.com/paper/1502.02454/) (2015)
- [Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder](https://mlsanity.com/paper/2011.11878/) (2020)
- [Interpreting Attention Layer Outputs with Sparse Autoencoders](https://mlsanity.com/paper/2406.17759/) (2024)

## Built on by (most cited first, 1 of 1)

- [Reconciling Consistency-Based Diagnosis with Actual-Causality-Based Explanations](https://mlsanity.com/paper/2605.08688/) (2026)

## Abstract (arXiv)

As artificial intelligence (AI), including machine learning (ML) models and foundation models (FMs), are increasingly deployed in high-stakes domains, ensuring their trustworthiness has become a central challenge. However, the core trustworthy AI objectives, such as fairness, robustness, privacy, and explainability, are hard to achieve simultaneously, especially while preserving utility. This position paper argues that causality is necessary to understand and balance trade-offs in performance and multiple objectives of trustworthy AI. We ground our arguments in re-interpreting trustworthy AI trade-offs as incompatible invariance requirements under different changes to the data-generating process. We then illustrate this argument through case-study analyses from the literature and a stylized synthetic-data simulation, showing that causality provides a unifying framework for understanding how trade-offs in trustworthy AI arise and how they can be softened or resolved through selective invariance. This perspective applies to both classical ML models and large-scale FMs. Finally, we outline open challenges and opportunities for using causality to build both trustworthy and high-performing AI.