CTRL-Rec: Controlling Recommender Systems With Natural Language

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Carroll, Micah, Foote, Adeline, Feng, Kevin, Williams, Marcus, Dragan, Anca, Knox, W. Bradley, Milli, Smitha
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912647063011328
author Carroll, Micah
Foote, Adeline
Feng, Kevin
Williams, Marcus
Dragan, Anca
Knox, W. Bradley
Milli, Smitha
author_facet Carroll, Micah
Foote, Adeline
Feng, Kevin
Williams, Marcus
Dragan, Anca
Knox, W. Bradley
Milli, Smitha
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12742
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CTRL-Rec: Controlling Recommender Systems With Natural Language
Carroll, Micah
Foote, Adeline
Feng, Kevin
Williams, Marcus
Dragan, Anca
Knox, W. Bradley
Milli, Smitha
Artificial Intelligence
Information Retrieval
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.
title CTRL-Rec: Controlling Recommender Systems With Natural Language
topic Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2510.12742