Counterfactual Latent Representations: A Neurosymbolic Approach

Leonhard Kestel, Christoph Kern
Proceedings of Fifth European Conference on Algorithmic Fairness, PMLR 350:45-50, 2026.

Abstract

Counterfactual fairness, i.e., asking how a prediction would change under interventions on sensitive attributes, is hard to opera- tionalize for unstructured inputs such as text. We propose a modular neurosymbolic framework that decouples representation learning from causal intervention: a pretrained encoder maps text to a latent representation, a semantic decoder grounds part of this space in a structured causal subgraph, and a neural manipulator learns to transform the latent representation analogously to a symbolic counterfactual operation on the decoded features, trained under a consistency constraint between the two. The approach localizes causal assumptions in an explicit subgraph, trading end-to-end optimization for auditability.

Cite this Paper

BibTeX
@InProceedings{pmlr-v350-kestel26a, title = {Counterfactual Latent Representations: A Neurosymbolic Approach}, author = {Kestel, Leonhard and Kern, Christoph}, booktitle = {Proceedings of Fifth European Conference on Algorithmic Fairness}, pages = {45--50}, year = {2026}, editor = {De Bie, Tijl and Defrance, MaryBeth and Calders, Toon and Nguyen, Dennis}, volume = {350}, series = {Proceedings of Machine Learning Research}, month = {02--04 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v350/main/assets/kestel26a/kestel26a.pdf}, url = {https://proceedings.mlr.press/v350/kestel26a.html}, abstract = {Counterfactual fairness, i.e., asking how a prediction would change under interventions on sensitive attributes, is hard to opera- tionalize for unstructured inputs such as text. We propose a modular neurosymbolic framework that decouples representation learning from causal intervention: a pretrained encoder maps text to a latent representation, a semantic decoder grounds part of this space in a structured causal subgraph, and a neural manipulator learns to transform the latent representation analogously to a symbolic counterfactual operation on the decoded features, trained under a consistency constraint between the two. The approach localizes causal assumptions in an explicit subgraph, trading end-to-end optimization for auditability.} }
Endnote
%0 Conference Paper %T Counterfactual Latent Representations: A Neurosymbolic Approach %A Leonhard Kestel %A Christoph Kern %B Proceedings of Fifth European Conference on Algorithmic Fairness %C Proceedings of Machine Learning Research %D 2026 %E Tijl De Bie %E MaryBeth Defrance %E Toon Calders %E Dennis Nguyen %F pmlr-v350-kestel26a %I PMLR %P 45--50 %U https://proceedings.mlr.press/v350/kestel26a.html %V 350 %X Counterfactual fairness, i.e., asking how a prediction would change under interventions on sensitive attributes, is hard to opera- tionalize for unstructured inputs such as text. We propose a modular neurosymbolic framework that decouples representation learning from causal intervention: a pretrained encoder maps text to a latent representation, a semantic decoder grounds part of this space in a structured causal subgraph, and a neural manipulator learns to transform the latent representation analogously to a symbolic counterfactual operation on the decoded features, trained under a consistency constraint between the two. The approach localizes causal assumptions in an explicit subgraph, trading end-to-end optimization for auditability.
APA
Kestel, L. & Kern, C.. (2026). Counterfactual Latent Representations: A Neurosymbolic Approach. Proceedings of Fifth European Conference on Algorithmic Fairness, in Proceedings of Machine Learning Research 350:45-50 Available from https://proceedings.mlr.press/v350/kestel26a.html.

Related Material