# Causality-Driven Neural Network Repair: Challenges and Opportunities

arXiv: https://arxiv.org/abs/2504.17946 · HTML: https://mlsanity.com/paper/2504.17946/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning.
- Builds on 13 of its 28 references that are in the map.
- First posted on arXiv 24 Apr 2025.

## Placed in

- LLM reasoning / [Causal reasoning in LLMs](https://mlsanity.com/lr/causal-reasoning-in-llms/)

## Builds on (most cited first, 13 of 13)

- [A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI](https://mlsanity.com/paper/1907.07374/) (2019)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [Deep Structural Causal Models for Tractable Counterfactual Inference](https://mlsanity.com/paper/2006.06485/) (2020)
- [Revisiting the "Video" in Video-Language Understanding](https://mlsanity.com/paper/2206.01720/) (2022)
- [Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review](https://mlsanity.com/paper/2005.09830/) (2020)
- [CausalAdv: Adversarial Robustness through the Lens of Causality](https://mlsanity.com/paper/2106.06196/) (2021)
- [Challenges of Using Text Classifiers for Causal Inference](https://mlsanity.com/paper/1810.00956/) (2018)
- [Arachne: Search Based Repair of Deep Neural Networks](https://mlsanity.com/paper/1912.12463/) (2019)
- [Causal Reasoning Meets Visual Representation Learning: A Prospective Study](https://mlsanity.com/paper/2204.12037/) (2022)
- [Causal Testing: Finding Defects' Root Causes](https://mlsanity.com/paper/1809.06991/) (2018)
- [Explaining Deep Learning Models using Causal Inference](https://mlsanity.com/paper/1811.04376/) (2018)
- [Causal Learning for Socially Responsible AI](https://mlsanity.com/paper/2104.12278/) (2021)
- [Where and How to Attack? A Causality-Inspired Recipe for Generating Counterfactual Adversarial Examples](https://mlsanity.com/paper/2312.13628/) (2023)

## Abstract (arXiv)

Deep Neural Networks (DNNs) often rely on statistical correlations rather than causal reasoning, limiting their robustness and interpretability. While testing methods can identify failures, effective debugging and repair remain challenging. This paper explores causal inference as an approach primarily for DNN repair, leveraging causal debugging, counterfactual analysis, and structural causal models (SCMs) to identify and correct failures. We discuss in what ways these techniques support fairness, adversarial robustness, and backdoor mitigation by providing targeted interventions. Finally, we discuss key challenges, including scalability, generalization, and computational efficiency, and outline future directions for integrating causality-driven interventions to enhance DNN reliability.