# A Causal Analysis of Harm

arXiv: https://arxiv.org/abs/2210.05327 · HTML: https://mlsanity.com/paper/2210.05327/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 48 references that are in the map.
- First posted on arXiv 11 Oct 2022.

## Builds on (most cited first, 6 of 6)

- [Abstracting Causal Models](https://mlsanity.com/paper/1812.03789/) (2018)
- [A Modification of the Halpern-Pearl Definition of Causality](https://mlsanity.com/paper/1505.00162/) (2015)
- [Causal Sufficiency and Actual Causation](https://mlsanity.com/paper/2102.02311/) (2021)
- [Counterfactual harm](https://mlsanity.com/paper/2204.12993/) (2022)
- [Graded Causation and Defaults](https://mlsanity.com/paper/1309.1226/) (2013)
- [Quantifying Harm](https://mlsanity.com/paper/2209.15111/) (2022)

## Built on by (most cited first, 15 of 15)

- [Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems](https://mlsanity.com/paper/2405.06624/) (2024)
- [Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Sets](https://mlsanity.com/paper/2406.06671/) (2024)
- [SkiLD: Unsupervised Skill Discovery Guided by Factor Interactions](https://mlsanity.com/paper/2410.18416/) (2024)
- [A Measure-Theoretic Axiomatisation of Causality](https://mlsanity.com/paper/2305.17139/) (2023)
- [On the Pros and Cons of Active Learning for Moral Preference Elicitation](https://mlsanity.com/paper/2407.18889/) (2024)
- [Harm Mitigation in Recommender Systems under User Preference Dynamics](https://mlsanity.com/paper/2406.09882/) (2024)
- [Counterfactual Effect Decomposition in Multi-Agent Sequential Decision Making](https://mlsanity.com/paper/2410.12539/) (2024)
- [The Limits of Predicting Agents from Behaviour](https://mlsanity.com/paper/2506.02923/) (2025)
- [Analyzing Intentional Behavior in Autonomous Agents under Uncertainty](https://mlsanity.com/paper/2307.01532/) (2023)
- [Nondeterministic Causal Models](https://mlsanity.com/paper/2405.14001/) (2024)
- [Matchings, Predictions and Counterfactual Harm in Refugee Resettlement Processes](https://mlsanity.com/paper/2407.13052/) (2024)
- [Towards Developing Ethical Reasoners: Integrating Probabilistic Reasoning and Decision-Making for Complex AI Systems](https://mlsanity.com/paper/2502.21250/) (2025)
- [A Counterfactual Cause in Situation Calculus](https://mlsanity.com/paper/2501.06857/) (2025)
- [Actual causality in fault trees](https://mlsanity.com/paper/2607.01840/) (2026)
- [Path-specific harm decomposition: A partial identification framework](https://mlsanity.com/paper/2609.29938/) (2026)

## Abstract (arXiv)

As autonomous systems rapidly become ubiquitous, there is a growing need for a legal and regulatory framework to address when and how such a system harms someone. There have been several attempts within the philosophy literature to define harm, but none of them has proven capable of dealing with with the many examples that have been presented, leading some to suggest that the notion of harm should be abandoned and "replaced by more well-behaved notions". As harm is generally something that is caused, most of these definitions have involved causality at some level. Yet surprisingly, none of them makes use of causal models and the definitions of actual causality that they can express. In this paper we formally define a qualitative notion of harm that uses causal models and is based on a well-known definition of actual causality (Halpern, 2016). The key novelty of our definition is that it is based on contrastive causation and uses a default utility to which the utility of actual outcomes is compared. We show that our definition is able to handle the examples from the literature, and illustrate its importance for reasoning about situations involving autonomous systems.