Post-Training Denoising of User Profiles with LLMs in Collaborative Filtering Recommendation

TL;DR

This paper introduces a post-training denoising method using Large Language Models to improve collaborative filtering recommendations by refining user profiles without altering the original model or requiring additional training.

Contribution

The work presents a novel post-training denoising approach leveraging LLMs to enhance user profiles for recommender systems without changing the model architecture or training process.

Findings

Up to 13% improvement in recommendation effectiveness.

Effective across multiple LLMs and datasets.

Does not require additional data or model fine-tuning.

Abstract

Implicit feedback -- the main data source for training Recommender Systems (RSs) -- is inherently noisy and has been shown to negatively affect recommendation effectiveness. Denoising has been proposed as a method for removing noisy implicit feedback and improving recommendations. Prior work has focused on in-training denoising, however this requires additional data, changes to the model architecture and training procedure or fine-tuning, all of which can be costly and data hungry. In this work, we focus on post-training denoising. Different from in-training denoising, post-training denoising does not involve changing the architecture of the model nor its training procedure, and does not require additional data. Specifically, we present a method for post-training denoising user profiles using Large Language Models (LLMs) for Collaborative Filtering (CF) recommendations. Our approach prompts LLMs with (i) a user profile (user interactions), (ii) a candidate item, and (iii) its rank as given by the CF recommender, and asks the LLM to remove items from the user profile to improve the rank of the candidate item. Experiments with a state-of-the-art CF recommender and 4 open and closed source LLMs in 3 datasets show that our denoising yields improvements up to 13% in effectiveness over the original user profiles. Our code is available at https://github.com/edervishaj/denoising-user-profiles-LLM.