mlsanityData to 7 Oct 2026

GenCAR: Generative Counterfactual Alignment with Risk-Controlled Selection for Out-of-Distribution Recommendation

arXiv 2609.02162 ↗First posted 2 Sep 2026cs.IR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Serving useful recommendations under distribution shift is crucial for balancing utility and risk in out-of-distribution (OOD) recommendation. However, most existing OOD methods improve ranking or construct counterfactual candidates without controlling the proxy-label false discovery rate (FDR) of the served set. In this work, we formulate OOD serving as the α-Valid Counterfactual Recommendation (α-VCR) problem to retain candidate support learned from counterfactual supervision while controlling proxy-label FDR, and propose GenCAR, which couples preference-grounded counterfactual supervision with calibrated set selection. In particular, GenCAR fixes the stable-preference representation while intervening on the environmental factor, grounds offline large language model proposals through preference anchors and trust-radius filtering, and uses conformal p-values for Benjamini--Hochberg selection. We theoretically bound conditional counterfactual approximation error and prove finite-sample, distribution-free control of proxy-label FDR under exchangeability and positive regression dependence, with a Benjamini--Yekutieli guarantee under arbitrary dependence. Extensive experiments audit realized proxy false discovery proportions and demonstrate that GenCAR consistently enhances OOD candidate recovery across diverse benchmarks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 38 of its 57 references that are in the map. First posted on arXiv 2 Sep 2026.

Builds on

38 of 57 references.

References · 38

  1. 2019Invariant Risk Minimizationcited by 1,832
  2. 2018Self-Attentive Sequential Recommendationcited by 1,169
  3. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 517
  4. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
  5. 2023Large Language Models are Zero-Shot Rankers for Recommender Systemscited by 307
  6. 2016Recommendations as Treatments: Debiasing Learning and Evaluationcited by 246
  7. 2023Recommender Systems with Generative Retrievalcited by 191
  8. 2024Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendationscited by 184
  9. 2023LLMRec: Large Language Models with Graph Augmentation for Recommendationcited by 171
  10. 2023Adapting Large Language Models by Integrating Collaborative Semantics for Recommendationcited by 171
  11. 2023How Can Recommender Systems Benefit from Large Language Models: A Surveycited by 141
  12. 2021Testing for Outliers with Conformal p-valuescited by 133
26 more
  1. 2023CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendationcited by 99
  2. 2020Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender Systemcited by 94
  3. 2023DiffuRec: A Diffusion Model for Sequential Recommendationcited by 91
  4. 2017Causal Embeddings for Recommendationcited by 79
  5. 2023ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendationcited by 76
  6. 2023Towards Open-World Recommendation with Knowledge Augmentation from Large Language Modelscited by 74
  7. 2023Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusioncited by 72
  8. 2022Selection by Prediction with Conformal p-valuescited by 66
  9. 2024A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)cited by 58
  10. 2023LLaRA: Large Language-Recommendation Assistantcited by 56
  11. 2024Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender Systemcited by 50
  12. 2024Conformal Alignment: Knowing When to Trust Foundation Models with Guaranteescited by 50
  13. 2023Diffusion Augmentation for Sequential Recommendationcited by 37
  14. 2024Plug-in Diffusion Model for Sequential Recommendationcited by 37
  15. 2024Denoising Diffusion Recommender Modelcited by 28
  16. 2024Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them)cited by 26
  17. 2023Invariant Collaborative Filtering to Popularity Distribution Shiftcited by 23
  18. 2023A Survey on Causal Inference for Recommendationcited by 22
  19. 2024Language Representations Can be What Recommenders Need: Findings and Potentialscited by 18
  20. 2024Distributionally Robust Graph-based Recommendation Systemcited by 17
  21. 2024Breaking the Barrier: Utilizing Large Language Models for Industrial Recommendation Systems through an Inferential Knowledge Graphcited by 16
  22. 2024Graph Representation Learning via Causal Diffusion for Out-of-Distribution Recommendationcited by 11
  23. 2023Causal Disentangled Recommendation Against User Preference Shiftscited by 8
  24. 2024Preference Diffusion for Recommendationcited by 8
  25. 2024Collaborative Cross-modal Fusion with Large Language Model for Recommendationcited by 4
  26. 2025You Don't Bring Me Flowers: Mitigating Unwanted Recommendations Through Conformal Risk Controlcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Neutralizing Popularity Bias in LLM-based Recommendation via Counterfactual Reasoning Guidelines
  2. 2024Guided Diffusion-based Counterfactual Augmentation for Robust Session-based Recommendation
  3. 2022CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation
  4. 2025Enhancing Temporal Sensitivity of Large Language Model for Recommendation with Counterfactual Tuning
  5. 2026Causal Direct Preference Optimization for Distributionally Robust Generative Recommendation
  6. 2026Robust Post-Training for Generative Recommenders: Why Exponential Reward-Weighted SFT Outperforms RLHF
  7. 2026EchoRec: Multi-Item Prediction-Empowered Generative Recommendation via Cycle-Consistent Preference Alignment
  8. 2026Aligning Multimodal Sequential Recommendations via Robust Direct Preference Optimization with Sparse MoE