mlsanityData to 7 Oct 2026

A Survey of Controllable Learning: Methods and Applications in Information Retrieval

arXiv 2407.06083 ↗First posted 4 Jul 2024cs.LG cs.IRcited by 12

Not on the map. Why?

Abstract (arXiv)

Controllability has become a crucial aspect of trustworthy machine learning, enabling learners to meet predefined targets and adapt dynamically at test time without requiring retraining as the targets shift. We provide a formal definition of controllable learning (CL), and discuss its applications in information retrieval (IR) where information needs are often complex and dynamic. The survey categorizes CL according to what is controllable (e.g., multiple objectives, user portrait, scenario adaptation), who controls (users or platforms), how control is implemented (e.g., rule-based method, Pareto optimization, hypernetwork and others), and where to implement control (e.g., pre-processing, in-processing, post-processing methods). Then, we identify challenges faced by CL across training, evaluation, task setting, and deployment in online environments. Additionally, we outline promising directions for CL in theoretical analysis, efficient computation, empowering large language models, application scenarios and evaluation frameworks.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 49 of its 103 references that are in the map. First posted on arXiv 4 Jul 2024.

Builds on

49 of 103 references.

References · 49

  1. 2023A Survey of Large Language Modelscited by 2,537
  2. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  3. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  4. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  5. 2017Deep Interest Network for Click-Through Rate Predictioncited by 541
  6. 2023BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editingcited by 438
  7. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 329
  8. 2023Diffusion Self-Guidance for Controllable Image Generationcited by 305
  9. 2021Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworkscited by 278
  10. 2017Toward Controlled Generation of Textcited by 271
  11. 2019Pareto Multi-Task Learningcited by 224
  12. 2024Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoderscited by 213
37 more
  1. 2018Explainable Recommendation: A Survey and New Perspectivescited by 210
  2. 2018Adaptive Online Learning in Dynamic Environmentscited by 130
  3. 2020Learning the Pareto Front with Hypernetworkscited by 122
  4. 2022Task-aware Retrieval with Instructionscited by 107
  5. 2022A Survey on the Fairness of Recommender Systemscited by 102
  6. 2023A Brief Review of Hypernetworks in Deep Learningcited by 102
  7. 2018Learning Tree-based Deep Model for Recommender Systemscited by 99
  8. 2020Controllable Multi-Interest Framework for Recommendationcited by 92
  9. 2023Controlled Text Generation with Natural Language Instructionscited by 87
  10. 2019The relationship between trust in AI and trustworthy machine learning technologiescited by 78
  11. 2022HyperPrompt: Prompt-based Task-Conditioning of Transformerscited by 67
  12. 2024FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructionscited by 67
  13. 2023PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Informationcited by 60
  14. 2020Efficient Continuous Pareto Exploration in Multi-Task Learningcited by 57
  15. 2020Controllable Pareto Multi-Task Learningcited by 51
  16. 2021Scalable Pareto Front Approximation for Deep Multi-Objective Learningcited by 45
  17. 2022A Survey on Trustworthy Recommender Systemscited by 40
  18. 2021Non-stationary Online Learning with Memory and Non-stochastic Controlcited by 33
  19. 2023Model-as-a-Service (MaaS): A Surveycited by 24
  20. 2022User-controllable Recommendation Against Filter Bubblescited by 22
  21. 2023HAMUR: Hyper Adapter for Multi-Domain Recommendationcited by 21
  22. 2024Aligning Large Language Models for Controllable Recommendationscited by 19
  23. 2022Improving Pareto Front Learning via Multi-Sample Hypernetworkscited by 16
  24. 2023Editable User Profiles for Controllable Text Recommendationcited by 16
  25. 2023Controllable Multi-Objective Re-ranking with Policy Hypernetworkscited by 15
  26. 2020Achieving Fairness via Post-Processing in Web-Scale Recommender Systemscited by 13
  27. 2024UniSAR: Modeling User Transition Behaviors between Search and Recommendationcited by 12
  28. 2023HyperBandit: Contextual Bandit with Hypernewtork for Time-Varying User Preferences in Streaming Recommendationcited by 10
  29. 2021Privacy-Preserving Synthetic Location Data in the Real Worldcited by 8
  30. 2024On Practical Diversified Recommendation with Controllable Category Diversity Frameworkcited by 7
  31. 2021Controllable Gradient Item Retrievalcited by 5
  32. 2023Deep Task-specific Bottom Representation Network for Multi-Task Recommendationcited by 5
  33. 2024QAGCF: Graph Collaborative Filtering for Q&A Recommendationcited by 5
  34. 2024Combining Embedding-Based and Semantic-Based Models for Post-hoc Explanations in Recommender Systemscited by 4
  35. 2023User-Controllable Recommendation via Counterfactual Retrospective and Prospective Explanationscited by 3
  36. 2021Controllable Recommenders using Deep Generative Models and Disentanglementcited by 2
  37. 2023Information Extraction from Unstructured data using Augmented-AI and Computer Visioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 5.

12 papers.

  1. 2025ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewardingcited by 32
  2. 2025Retrieval Augmented Generation with Collaborative Filtering for Personalized Text Generationcited by 23
  3. 2025Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generationcited by 13
  4. 2025Interactive Recommendation Agent with Active User Commandscited by 10
  5. 2024World Models: The Safety Perspectivecited by 9
  6. 2025KuaiLive: A Real-time Interactive Dataset for Live Streaming Recommendationcited by 5
  7. 2025MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation Alignmentcited by 3
  8. 2026Enhancing Bandit Algorithms with LLMs for Time-varying User Preferences in Streaming Recommendationscited by 1
  9. 2026GenRecEdit: Adapting Model Editing for Generative Recommendation with Cold-Start Itemscited by 1
  10. 2026ClusterRAG: Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generationcited by 0
  11. 2026Can We Steer the Black-Box? Towards Controllability-Centric Evaluation of Recommender Systems with Collaborative Agentscited by 0
  12. 2026CRAMER: Control via Request-Aware Masking for Editing Recommenderscited by 0