# SelfDR: Self-Distillation from Reasoning for LLM-Based Recommendation

arXiv: https://arxiv.org/abs/2609.03313 · HTML: https://mlsanity.com/paper/2609.03313/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- Builds on 17 of its 60 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Placed in

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

## Builds on (most cited first, 17 of 17)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation](https://mlsanity.com/paper/1905.08094/) (2019)
- [A Survey on Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2402.13116/) (2024)
- [Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation](https://mlsanity.com/paper/2311.09049/) (2023)
- [LlamaRec: Two-Stage Recommendation using Large Language Models for Ranking](https://mlsanity.com/paper/2311.02089/) (2023)
- [Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation](https://mlsanity.com/paper/2509.19296/) (2025)
- [Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learning](https://mlsanity.com/paper/2503.24289/) (2025)
- [Reason4Rec: Deliberative User Preference Alignment of Large Language Models for Recommendation](https://mlsanity.com/paper/2502.02061/) (2025)
- [DotaMath: Decomposition of Thought with Code Assistance and Self-correction for Mathematical Reasoning](https://mlsanity.com/paper/2407.04078/) (2024)
- [Slow Thinking for Sequential Recommendation](https://mlsanity.com/paper/2504.09627/) (2025)
- [A Comprehensive Review of Knowledge Distillation in Computer Vision](https://mlsanity.com/paper/2404.00936/) (2024)
- [Bidirectional Knowledge Distillation for Enhancing Sequential Recommendation with Large Language Models](https://mlsanity.com/paper/2505.18120/) (2025)
- [Bridging the Gap: Self-Optimized Fine-Tuning for LLM-based Recommender Systems](https://mlsanity.com/paper/2505.20771/) (2025)
- [Feature Interaction Fusion Self-Distillation Network For CTR Prediction](https://mlsanity.com/paper/2411.07508/) (2024)

## Abstract (arXiv)

Large Language Models (LLMs) have recently emerged as powerful backbones for recommendation. To better elicit their capabilities, reasoning has been widely incorporated to help LLMs interpret rich textual signals and improve recommendation accuracy. However, explicitly generating intermediate reasoning traces often incurs substantial computational costs, which limits practical deployment in real-world recommender systems. To address this challenge, we propose SelfDR, a Self-Distillation from Reasoning framework for LLM-based Recommendation. SelfDR distills an LLM's own reasoning-enhanced predictions to produce recommendations directly, improving recommendation effectiveness while maintaining inference efficiency. All components in the framework are built on the same base LLM, without relying on any external models. Specifically, the teacher recommender is constructed by training a reasoner with downstream performance as the reward, enabling it to generate targeted rationales that are later incorporated into the teacher's input. A student recommender for direct recommendation, with the same underlying model, then learns from the teacher through self-distillation with a dynamic weighting strategy. Extensive experiments on three public datasets validate the effectiveness, rationality, and efficiency of SelfDR. Codes are available at https://github.com/JiangDeccc/SelfDistillation.