CTRL-Rec: Controlling Recommender Systems With Natural Language

• URL: http://arxiv.org/abs/2510.12742v1
• Date: Tue, 14 Oct 2025 17:20:04 GMT
• Title: CTRL-Rec: Controlling Recommender Systems With Natural Language
• Abstract summary: We propose a method that allows for natural language control of traditional recommender systems in real-time.<n>We integrate user-request-based predictions into the standard weighting of signals that traditional recommender systems optimize.<n>In a study with 19 Letterboxd users, we find that the method significantly enhanced users' sense of control and satisfaction with recommendations.
• Score: 8.711335780004674
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When users are dissatisfied with recommendations from a recommender system, they often lack fine-grained controls for changing them. Large language models (LLMs) offer a solution by allowing users to guide their recommendations through natural language requests (e.g., "I want to see respectful posts with a different perspective than mine"). We propose a method, CTRL-Rec, that allows for natural language control of traditional recommender systems in real-time with computational efficiency. Specifically, at training time, we use an LLM to simulate whether users would approve of items based on their language requests, and we train embedding models that approximate such simulated judgments. We then integrate these user-request-based predictions into the standard weighting of signals that traditional recommender systems optimize. At deployment time, we require only a single LLM embedding computation per user request, allowing for real-time control of recommendations. In experiments with the MovieLens dataset, our method consistently allows for fine-grained control across a diversity of requests. In a study with 19 Letterboxd users, we find that CTRL-Rec was positively received by users and significantly enhanced users' sense of control and satisfaction with recommendations compared to traditional controls.

Related papers

• CRAMER: Control via Request-Aware Masking for Editing Recommenders [3.5057035107656733]
  This paper presents Control via Request-Aware Masking for Editing Recommenders (CRAMER)<n>CRAMER treats user requests as control signals to modulate frozen backbone parameters through masking.<n>It achieves instant adaptation to diverse requests while avoiding costly retraining.
  arXiv  Detail & Related papers  (2026-08-26T04:43:23Z)
• User Simulator-Guided Multi-Turn Preference Optimization for Reasoning LLM-based Conversational Recommendation [5.313432318455876]
  We propose a user simulator-guided multi-turn preference optimization conversational recommendation framework.<n>To align simulator-generated feedback with true user preferences in the absence of explicit labels, we enhance feedback quality via multi-task supervised fine-tuning.
  arXiv  Detail & Related papers  (2026-04-04T09:52:30Z)
• Token-Controlled Re-ranking for Sequential Recommendation via LLMs [32.61510378078676]
  COREC is a novel token-augmented re-ranking framework that incorporates specific user requirements in co-creating the recommendation outcome.<n> COREC empowers users to steer re-ranking results with precise and flexible control via explicit, attribute-based signals.<n> Experiments show that COREC exceeds state-of-the-art baselines on standard recommendation effectiveness.
  arXiv  Detail & Related papers  (2025-11-22T04:31:19Z)
• RLHF Fine-Tuning of LLMs for Alignment with Implicit User Feedback in Conversational Recommenders [0.8246494848934447]
  We propose a fine-tuning solution using human feedback reinforcement learning (RLHF) to maximize implied user feedback (IUF) in a multi-turn recommendation context.<n>We show that our RLHF-fine-tuned models can perform better in terms of top-$k$ recommendation accuracy, coherence, and user satisfaction compared to (arrow-zero-cmwrquca-teja-falset ensuite 2Round group-deca States penalty give up.
  arXiv  Detail & Related papers  (2025-08-07T11:36:55Z)
• Multi-agents based User Values Mining for Recommendation [52.26100802380767]
  We propose a zero-shot multi-LLM collaborative framework for effective and accurate user value extraction.<n>We apply text summarization techniques to condense item content while preserving essential meaning.<n>To mitigate hallucinations, we introduce two specialized agent roles: evaluators and supervisors.
  arXiv  Detail & Related papers  (2025-05-02T04:01:31Z)
• Laser: Parameter-Efficient LLM Bi-Tuning for Sequential Recommendation with Collaborative Information [76.62949982303532]
  We propose a parameter-efficient Large Language Model Bi-Tuning framework for sequential recommendation with collaborative information (Laser) In our Laser, the prefix is utilized to incorporate user-item collaborative information and adapt the LLM to the recommendation task, while the suffix converts the output embeddings of the LLM from the language space to the recommendation space for the follow-up item recommendation. M-Former is a lightweight MoE-based querying transformer that uses a set of query experts to integrate diverse user-specific collaborative information encoded by frozen ID-based sequential recommender systems.
  arXiv  Detail & Related papers  (2024-09-03T04:55:03Z)
• PeaPOD: Personalized Prompt Distillation for Generative Recommendation [11.27949757550442]
  We propose a PErsonAlized PrOmpt Distillation (PeaPOD) approach to distill user preferences as personalized soft prompts.<n>Considering the complexities of user preferences in the real world, we maintain a shared set of learnable prompts that are dynamically weighted based on the user's interests.<n> Experimental results on three real-world datasets demonstrate the effectiveness of our PeaPOD model on sequential recommendation, top-n recommendation, and explanation generation tasks.
  arXiv  Detail & Related papers  (2024-07-06T09:58:58Z)
• Vague Preference Policy Learning for Conversational Recommendation [48.868921530958666]
  Conversational recommendation systems commonly assume users have clear preferences, leading to potential over-filtering.<n>We introduce the Vague Preference Multi-round Conversational Recommendation (VPMCR) scenario, employing a soft estimation mechanism to accommodate users' vague and dynamic preferences.<n>Our work advances CRS by accommodating users' inherent ambiguity and relative decision-making processes, improving real-world applicability.
  arXiv  Detail & Related papers  (2023-06-07T14:57:21Z)
• Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach [83.62750225073341]
  We consider recommendation as instruction following by large language models (LLMs) We first design a general instruction format for describing the preference, intention, task form and context of a user in natural language. Then we manually design 39 instruction templates and automatically generate a large amount of user-personalized instruction data.
  arXiv  Detail & Related papers  (2023-05-11T17:39:07Z)
• Editable User Profiles for Controllable Text Recommendation [66.00743968792275]
  We propose LACE, a novel concept value bottleneck model for controllable text recommendations. LACE represents each user with a succinct set of human-readable concepts. It learns personalized representations of the concepts based on user documents.
  arXiv  Detail & Related papers  (2023-04-09T14:52:18Z)
• Talk the Walk: Synthetic Data Generation for Conversational Music Recommendation [62.019437228000776]
  We present TalkWalk, which generates realistic high-quality conversational data by leveraging encoded expertise in widely available item collections. We generate over one million diverse conversations in a human-collected dataset.
  arXiv  Detail & Related papers  (2023-01-27T01:54:16Z)
• Improving Sequential Query Recommendation with Immediate User Feedback [6.925738064847176]
  We propose an algorithm for next query recommendation in interactive data exploration settings. We conduct a large-scale experimental study using log files from a popular online literature discovery service.
  arXiv  Detail & Related papers  (2022-05-12T18:19:24Z)
• Reward Constrained Interactive Recommendation with Natural Language Feedback [158.8095688415973]
  We propose a novel constraint-augmented reinforcement learning (RL) framework to efficiently incorporate user preferences over time. Specifically, we leverage a discriminator to detect recommendations violating user historical preference. Our proposed framework is general and is further extended to the task of constrained text generation.
  arXiv  Detail & Related papers  (2020-05-04T16:23:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.