mlsanityData to 14 Oct 2026

From Tokens to Policy: Causal and Interpretable Heterogeneous Treatment Effects Identification

arXiv 2606.17010 ↗First posted 15 Jun 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Heterogeneous Treatment Effect (HTE) identification is essential to explain the impact of an intervention and optimize our policies accordingly. Existing approaches trade expressivity for interpretability, but, if some active heterogeneity drivers are unmeasured, methods at both ends of this spectrum allow for spurious HTE characterization with no causal reading. In this work, we focus on controlled experiments and argue that an oracle HTE causal characterization via the latent interactors is now within reach, thanks to (i) more extensive pre-treatment measurements, i.e., multi-modal and multi-view, and (ii) scalable representations with minimal human supervision. We then re-frame HTE identification as a Markov-blanket discovery problem on a sufficient and aligned pre-treatment representation, and introduce Neural EXposure Interaction Search (NEXIS), an iterative procedure with a provable selection guarantee. We deploy NEXIS on two anti-poverty programs in Africa, augmenting each with satellite imagery capturing previously unmeasured environmental effect modifiers, leading to new candidate prescriptive guidelines to optimize the programs' next iterations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 37 of its 82 references that are in the map. First posted on arXiv 15 Jun 2026.

Builds on

37 of 82 references.

References · 37

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  6. 2025Qwen2.5-VL Technical Reportcited by 5,587
  7. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  8. 2023Sparse Autoencoders Find Highly Interpretable Features in Language Modelscited by 1,420
  9. 2023The Linear Representation Hypothesis and the Geometry of Large Language Modelscited by 716
  10. 2015Estimation and Inference of Heterogeneous Treatment Effects using Random Forestscited by 600
  11. 2024Scaling and evaluating sparse autoencoderscited by 553
  12. 2017Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learningcited by 478
25 more
  1. 2017Quasi-Oracle Estimation of Heterogeneous Treatment Effectscited by 332
  2. 2016Generalized Random Forestscited by 312
  3. 2015Recursive Partitioning for Heterogeneous Causal Effectscited by 255
  4. 2024Transcoders Find Interpretable LLM Feature Circuitscited by 200
  5. 2026Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnetcited by 191
  6. 2024A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoderscited by 160
  7. 2024Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applicationscited by 144
  8. 2025Learning Multi-Level Features with Matryoshka Sparse Autoencoderscited by 143
  9. 2024Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Controlcited by 86
  10. 2021Discussion on "Bayesian Regression Tree Models for Causal Inference: Regularization, Confounding, and Heterogeneous Effects" by Hahn, Murray and Carvalhocited by 77
  11. 2020Using satellite imagery to understand and promote sustainable developmentcited by 71
  12. 2025Sparse Autoencoders Learn Monosemantic Features in Vision-Language Modelscited by 71
  13. 2016The State of Applied Econometrics - Causality and Policy Evaluationcited by 41
  14. 2024Unifying Causal Representation Learning with the Invariance Principlecited by 31
  15. 2022Image-based Treatment Effect Heterogeneitycited by 20
  16. 2020Causal Rule Ensemble: Interpretable Discovery and Inference of Heterogeneous Treatment Effectscited by 13
  17. 2024Smoke and Mirrors in Causal Downstream Taskscited by 12
  18. 2022Variable importance measures for heterogeneous treatment effectscited by 10
  19. 2025Prediction-Powered Causal Inferencescited by 9
  20. 2019Heterogeneous causal effects with imperfect compliance: a Bayesian machine learning approachcited by 6
  21. 2025The Third Pillar of Causal Analysis? A Measurement Perspective on Causal Representationscited by 4
  22. 2025Exploratory Causal Inference in SAEncecited by 4
  23. 2023A nonparametric framework for treatment effect modifier discovery in high dimensionscited by 3
  24. 2024Measuring Variable Importance in Heterogeneous Treatment Effects with Confidencecited by 3
  25. 2026Causal Stability Selectioncited by 1

Built on by

Not cited yet.