# DaRec: A Disentangled Alignment Framework for Large Language Model and Recommender System

arXiv: https://arxiv.org/abs/2408.08231 · HTML: https://mlsanity.com/paper/2408.08231/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- First posted on arXiv 15 Aug 2024.

## Placed in

- LLM reasoning / [LLM reasoning for recommendation](https://mlsanity.com/lr/llm-reasoning-for-recommendation/)

## Built on by (most cited first, 11 of 11)

- [ALLVB: All-in-One Long Video Understanding Benchmark](https://mlsanity.com/paper/2503.07298/) (2025)
- [Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search](https://mlsanity.com/paper/2512.00968/) (2025)
- [EasyRec: Simple yet Effective Language Models for Recommendation](https://mlsanity.com/paper/2408.08821/) (2024)
- [Large Language Model Enhanced Recommender Systems: A Survey](https://mlsanity.com/paper/2412.13432/) (2024)
- [Pre-train, Align, and Disentangle: Empowering Sequential Recommendation with Large Language Models](https://mlsanity.com/paper/2412.04107/) (2024)
- [Automatically Identify and Rectify: Robust Deep Contrastive Multi-view Clustering in Noisy Scenarios](https://mlsanity.com/paper/2505.21387/) (2025)
- [Generalized Deep Multi-view Clustering via Causal Learning with Partially Aligned Cross-view Correspondence](https://mlsanity.com/paper/2509.16022/) (2025)
- [Divide-Then-Rule: A Cluster-Driven Hierarchical Interpolator for Attribute-Missing Graphs](https://mlsanity.com/paper/2507.10595/) (2025)
- [Parameter-Free Clustering via Self-Supervised Consensus Maximization (Extended Version)](https://mlsanity.com/paper/2511.09211/) (2025)
- [Iterative Semantic Reasoning from Individual to Group Interests for Generative Recommendation with LLMs](https://mlsanity.com/paper/2603.13934/) (2026)
- [P3Rec: Distilling Prior--Posterior Preference Reasoning for LLM-based Recommendation](https://mlsanity.com/paper/2609.13993/) (2026)

## Abstract (arXiv)

Benefiting from the strong reasoning capabilities, Large language models (LLMs) have demonstrated remarkable performance in recommender systems. Various efforts have been made to distill knowledge from LLMs to enhance collaborative models, employing techniques like contrastive learning for representation alignment. In this work, we prove that directly aligning the representations of LLMs and collaborative models is sub-optimal for enhancing downstream recommendation tasks performance, based on the information theorem. Consequently, the challenge of effectively aligning semantic representations between collaborative models and LLMs remains unresolved. Inspired by this viewpoint, we propose a novel plug-and-play alignment framework for LLMs and collaborative models. Specifically, we first disentangle the latent representations of both LLMs and collaborative models into specific and shared components via projection layers and representation regularization. Subsequently, we perform both global and local structure alignment on the shared representations to facilitate knowledge transfer. Additionally, we theoretically prove that the specific and shared representations contain more pertinent and less irrelevant information, which can enhance the effectiveness of downstream recommendation tasks. Extensive experimental results on benchmark datasets demonstrate that our method is superior to existing state-of-the-art algorithms.