Backtracking Counterfactuals

Julius Von Kügelgen, Abdirisak Mohamed, Sander Beckers
Proceedings of the Second Conference on Causal Learning and Reasoning, PMLR 213:177-196, 2023.

Abstract

Counterfactual reasoning—envisioning hypothetical scenarios, or possible worlds, where some circumstances are different from what (f)actually occurred (counter-to-fact)—is ubiquitous in human cognition. Conventionally, counterfactually-altered circumstances have been treated as “small miracles” that locally violate the laws of nature while sharing the same initial conditions. In Pearl’s structural causal model (SCM) framework this is made mathematically rigorous via interventions that modify the causal laws while the values of exogenous variables are shared. In recent years, however, this purely interventionist account of counterfactuals has increasingly come under scrutiny from both philosophers and psychologists. Instead, they suggest a backtracking account of counterfactuals, according to which the causal laws remain unchanged in the counterfactual world; differences to the factual world are instead “backtracked” to altered initial conditions (exogenous variables). In the present work, we explore and formalise this alternative mode of counterfactual reasoning within the SCM framework. Despite ample evidence that humans backtrack, the present work constitutes, to the best of our knowledge, the first general account and algorithmisation of backtracking counterfactuals. We discuss our backtracking semantics in the context of related literature and draw connections to recent developments in explainable artificial intelligence (XAI).

Cite this Paper

BibTeX
@InProceedings{pmlr-v213-kugelgen23a, title = {Backtracking Counterfactuals}, author = {K\"ugelgen, Julius Von and Mohamed, Abdirisak and Beckers, Sander}, booktitle = {Proceedings of the Second Conference on Causal Learning and Reasoning}, pages = {177--196}, year = {2023}, editor = {van der Schaar, Mihaela and Zhang, Cheng and Janzing, Dominik}, volume = {213}, series = {Proceedings of Machine Learning Research}, month = {11--14 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v213/kugelgen23a/kugelgen23a.pdf}, url = {https://proceedings.mlr.press/v213/kugelgen23a.html}, abstract = {Counterfactual reasoning—envisioning hypothetical scenarios, or possible worlds, where some circumstances are different from what (f)actually occurred (counter-to-fact)—is ubiquitous in human cognition. Conventionally, counterfactually-altered circumstances have been treated as “small miracles” that locally violate the laws of nature while sharing the same initial conditions. In Pearl’s structural causal model (SCM) framework this is made mathematically rigorous via interventions that modify the causal laws while the values of exogenous variables are shared. In recent years, however, this purely interventionist account of counterfactuals has increasingly come under scrutiny from both philosophers and psychologists. Instead, they suggest a backtracking account of counterfactuals, according to which the causal laws remain unchanged in the counterfactual world; differences to the factual world are instead “backtracked” to altered initial conditions (exogenous variables). In the present work, we explore and formalise this alternative mode of counterfactual reasoning within the SCM framework. Despite ample evidence that humans backtrack, the present work constitutes, to the best of our knowledge, the first general account and algorithmisation of backtracking counterfactuals. We discuss our backtracking semantics in the context of related literature and draw connections to recent developments in explainable artificial intelligence (XAI).} }
Endnote
%0 Conference Paper %T Backtracking Counterfactuals %A Julius Von Kügelgen %A Abdirisak Mohamed %A Sander Beckers %B Proceedings of the Second Conference on Causal Learning and Reasoning %C Proceedings of Machine Learning Research %D 2023 %E Mihaela van der Schaar %E Cheng Zhang %E Dominik Janzing %F pmlr-v213-kugelgen23a %I PMLR %P 177--196 %U https://proceedings.mlr.press/v213/kugelgen23a.html %V 213 %X Counterfactual reasoning—envisioning hypothetical scenarios, or possible worlds, where some circumstances are different from what (f)actually occurred (counter-to-fact)—is ubiquitous in human cognition. Conventionally, counterfactually-altered circumstances have been treated as “small miracles” that locally violate the laws of nature while sharing the same initial conditions. In Pearl’s structural causal model (SCM) framework this is made mathematically rigorous via interventions that modify the causal laws while the values of exogenous variables are shared. In recent years, however, this purely interventionist account of counterfactuals has increasingly come under scrutiny from both philosophers and psychologists. Instead, they suggest a backtracking account of counterfactuals, according to which the causal laws remain unchanged in the counterfactual world; differences to the factual world are instead “backtracked” to altered initial conditions (exogenous variables). In the present work, we explore and formalise this alternative mode of counterfactual reasoning within the SCM framework. Despite ample evidence that humans backtrack, the present work constitutes, to the best of our knowledge, the first general account and algorithmisation of backtracking counterfactuals. We discuss our backtracking semantics in the context of related literature and draw connections to recent developments in explainable artificial intelligence (XAI).
APA
Kügelgen, J.V., Mohamed, A. & Beckers, S.. (2023). Backtracking Counterfactuals. Proceedings of the Second Conference on Causal Learning and Reasoning, in Proceedings of Machine Learning Research 213:177-196 Available from https://proceedings.mlr.press/v213/kugelgen23a.html.

Related Material