mlsanityData to 14 Oct 2026

Uncertainty-Guided LLM Semantic Augmentation for Heterogeneous Treatment Effect Estimation

arXiv 2607.26599 ↗First posted 29 Jul 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Estimating heterogeneous treatment effects is central to targeted interventions, such as personalized promotions and precision medicine. We focus on the conditional average treatment effect (CATE), a standard estimand for characterizing such heterogeneity. Even under standard identification conditions, finite-sample CATE estimation requires learning the nuisance structure for covariate adjustment and treatment-effect heterogeneity, often together with an effective representation of X. Raw numerical and categorical encodings can leave semantic relations and higher-order interactions implicit, making this joint task locally unstable. A motivating study further shows that this instability appears through partially separable assignment- and heterogeneity-side channels. Building on this observation, we propose CURL (Causal Uncertainty-guided Representation Learning), a plug-in adapter that uses estimator uncertainty to allocate pretrained semantic capacity to locally unstable units. CURL queries a frozen LLM through two role-conditioned prompts, constructs assignment- and heterogeneity-oriented representations from the observed covariates, and routes them through separated pathways. On four benchmarks, CURL improves ten host learners in most settings, while ablation, refinement-dynamics, route-reassignment, and probe analyses support the intended design and roles of the two channels.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 58 references that are in the map. First posted on arXiv 29 Jul 2026.

Builds on

27 of 58 references.

References · 27

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  3. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  4. 2015Weight Uncertainty in Neural Networkscited by 554
  5. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 503
  6. 2017Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learningcited by 478
  7. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 410
  8. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 353
  9. 2017Quasi-Oracle Estimation of Heterogeneous Treatment Effectscited by 332
  10. 2021Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemblecited by 302
  11. 2019Adapting Neural Networks for the Estimation of Treatment Effectscited by 287
  12. 2017Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processescited by 158
15 more
  1. 2021Uncertainty Weighted Actor-Critic for Offline Reinforcement Learningcited by 126
  2. 2022Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learningcited by 125
  3. 2020Neural Contextual Bandits with Deep Representation and Shallow Explorationcited by 71
  4. 2020Treatment effect estimation with disentangled latent factorscited by 63
  5. 2020Identifying Causal-Effect Inference Failure with Uncertainty-Aware Modelscited by 57
  6. 2021A Critical Look at the Consistency of Causal Estimation With Deep Latent Variable Modelscited by 29
  7. 2024End-To-End Causal Effect Estimation from Unstructured Natural Language Datacited by 18
  8. 2023Causal Inference with Conditional Front-Door Adjustment and Identifiable Variational Autoencodercited by 17
  9. 2022DESCN: Deep Entire Space Cross Networks for Individual Treatment Effect Estimationcited by 16
  10. 2021β-Intact-VAE: Identifying and Estimating Causal Effects under Limited Overlapcited by 8
  11. 2024Proximal Causal Inference With Text Datacited by 7
  12. 2024Self-Distilled Disentangled Learning for Counterfactual Predictioncited by 4
  13. 2024Progressive Generalization Risk Reduction for Data-Efficient Causal Effect Estimationcited by 3
  14. 2022Improving Data-driven Heterogeneous Treatment Effect Estimation Under Structure Uncertaintycited by 2
  15. 2025Deep Disentangled Representation Network for Treatment Effect Estimationcited by 1

Built on by

Not cited yet.