# Unleashing the Power of Large Language Model for Denoising Recommendation

Source: [Unleashing the Power of Large Language Model for Denoising Recommendation](<https://www.sota2.com/research/paper/68fa76ed1e209131cea6ffe9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:06:07.870Z

Authors: Shuyao Wang, Zhi Zheng, Yongduo Sui, Hui Xiong

Published: 2025-02-13T08:19:45.000Z

## Abstract

Recommender systems are crucial for personalizing user experiences but often depend on implicit feedback data, which can be noisy and misleading. Existing denoising studies involve incorporating auxiliary information or learning strategies from interaction data. However, they struggle with the inherent limitations of external knowledge and interaction data, as well as the non-universality of certain predefined assumptions, hindering accurate noise identification. Recently, large language models (LLMs) have gained attention for their extensive world knowledge and reasoning abilities, yet their potential in enhancing denoising in recommendations remains underexplored. In this paper, we introduce LLaRD, a framework leveraging LLMs to improve denoising in recommender systems, thereby boosting overall recommendation performance. Specifically, LLaRD generates denoising-related knowledge by first enriching semantic insights from observational data via LLMs and inferring user-item preference knowledge. It then employs a novel Chain-of-Thought (CoT) technique over user-item interaction graphs to reveal relation knowledge for denoising. Finally, it applies the Information Bottleneck (IB) principle to align LLM-generated denoising knowledge with recommendation targets, filtering out noise and irrelevant LLM knowledge. Empirical results demonstrate LLaRD's effectiveness in enhancing denoising and recommendation accuracy.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Denoising Recommendation on DBbook 2014](<https://www.sota2.com/research/sota/denoising-recommendation-on-dbbook-2014.md>): Denoising Recommendation; DBbook 2014; Recall@10: 23.93.

- [Denoising Recommendation on Book-Crossing](<https://www.sota2.com/research/sota/denoising-recommendation-on-book-crossing.md>): Denoising Recommendation; Book-Crossing; Recall@10: 0.0809.

- [Denoising Recommendation on MovieLens 1M](<https://www.sota2.com/research/sota/denoising-recommendation-on-movielens-1m.md>): Denoising Recommendation; MovieLens 1M; Recall@10: 19.03.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2502.09058>)

[PDF](<https://arxiv.org/pdf/2502.09058.pdf>)
