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

• URL: http://arxiv.org/abs/2609.03313v1
• Date: Thu, 03 Sep 2026 03:05:17 GMT
• Title: SelfDR: Self-Distillation from Reasoning for LLM-Based Recommendation
• Abstract summary: SelfDR is a Self-Distillation from Reasoning framework for LLM-based Recommendation.<n>It distills an LLM's own reasoning-enhanced predictions to produce recommendations directly.<n>All components are built on the same base LLM, without relying on any external models.
• Score: 20.66655178579704
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Teacher-Guided Policy Optimization for LLM Distillation [90.49982387646861]
  Teacher-Guided Policy Optimization (TGPO) is an on-policy algorithm that incorporates dense directional guidance by leveraging teacher predictions conditioned on the student's rollout.<n>Experiments on complex reasoning benchmarks demonstrate that TGPO significantly outperforms standard baselines and is robust to different teachers.
  arXiv  Detail & Related papers  (2026-05-13T09:20:03Z)
• Think before Recommendation: Autonomous Reasoning-enhanced Recommender [25.883091131835172]
  RecZero is a reinforcement learning-based recommendation paradigm that abandons the traditional multi-model and multi-stage distillation approach.<n>The paper explores a hybrid paradigm, RecOne, which combines supervised fine-tuning with RL, initializing the model with cold-start reasoning samples and further optimizing it with RL.
  arXiv  Detail & Related papers  (2025-10-27T07:26:32Z)
• Beyond Static LLM Policies: Imitation-Enhanced Reinforcement Learning for Recommendation [23.945049006150555]
  Large language models (LLMs) have become critical tools for enhancing user engagement by delivering personalized content across diverse digital platforms.<n>Direct deployment of LLMs as primary recommendation policies presents notable challenges, including persistent latency issues.<n>This paper proposes a novel offline reinforcement learning framework that leverages imitation learning from LLM-generated trajectories.
  arXiv  Detail & Related papers  (2025-10-15T07:28:29Z)
• OneRec-Think: In-Text Reasoning for Generative Recommendation [55.53292983432484]
  OneRec-Think is a unified framework that seamlessly integrates dialogue, reasoning, and personalized recommendation.<n>Our proposed "Think-Ahead" architecture enables effective industrial deployment on Kuaishou, achieving a 0.159% gain in APP Stay Time.
  arXiv  Detail & Related papers  (2025-10-13T17:20:13Z)
• Towards Comprehensible Recommendation with Large Language Model Fine-tuning [41.218487308635126]
  We propose a novel Content Understanding from a Collaborative Perspective framework (CURec) for recommendation systems.<n>Curec generates collaborative-aligned content features for more comprehensive recommendations.<n>Experiments on public benchmarks demonstrate the superiority of CURec over existing methods.
  arXiv  Detail & Related papers  (2025-08-11T03:55:31Z)
• R$^2$ec: Towards Large Recommender Models with Reasoning [59.32598867813266]
  We propose R$2$ec, a unified large recommender model with intrinsic reasoning capability.<n>R$2$ec introduces a dual-head architecture that supports both reasoning chain generation and efficient item prediction in a single model.<n>To overcome the lack of annotated reasoning data, we design RecPO, a reinforcement learning framework.
  arXiv  Detail & Related papers  (2025-05-22T17:55:43Z)
• Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones? [58.80794196076336]
  Distilling large language models (LLMs) typically involves transferring the teacher model's responses through supervised fine-tuning (SFT)<n>We propose a novel distillation pipeline that transfers both responses and rewards.<n>Our method generates pseudo-rewards through a self-supervised mechanism that leverages the inherent structure of both teacher and student responses.
  arXiv  Detail & Related papers  (2025-02-26T20:50:11Z)
• Direct Preference Optimization for LLM-Enhanced Recommendation Systems [33.54698201942643]
  Large Language Models (LLMs) have exhibited remarkable performance across a wide range of domains.<n>We propose DPO4Rec, a framework that integrates DPO into LLM-enhanced recommendation systems.<n>Extensive experiments show that DPO4Rec significantly improves re-ranking performance over strong baselines.
  arXiv  Detail & Related papers  (2024-10-08T11:42:37Z)
• Re2LLM: Reflective Reinforcement Large Language Model for Session-based Recommendation [23.182787000804407]
  Large Language Models (LLMs) are emerging as promising approaches to enhance session-based recommendation (SBR) We propose a Reflective Reinforcement Large Language Model (Re2LLM) for SBR, guiding LLMs to focus on specialized knowledge essential for more accurate recommendations.
  arXiv  Detail & Related papers  (2024-03-25T05:12:18Z)
• Can Small Language Models be Good Reasoners for Sequential Recommendation? [34.098264212413305]
  Step-by-step knowLedge dIstillation fraMework for recommendation (SLIM) We introduce CoT prompting based on user behavior sequences for the larger teacher model. The rationales generated by the teacher model are then utilized as labels to distill the downstream smaller student model.
  arXiv  Detail & Related papers  (2024-03-07T06:49:37Z)
• Unlocking the Potential of Large Language Models for Explainable Recommendations [55.29843710657637]
  It remains uncertain what impact replacing the explanation generator with the recently emerging large language models (LLMs) would have. In this study, we propose LLMXRec, a simple yet effective two-stage explainable recommendation framework. By adopting several key fine-tuning techniques, controllable and fluent explanations can be well generated.
  arXiv  Detail & Related papers  (2023-12-25T09:09:54Z)
• LLMRec: Benchmarking Large Language Models on Recommendation Task [54.48899723591296]
  The application of Large Language Models (LLMs) in the recommendation domain has not been thoroughly investigated. We benchmark several popular off-the-shelf LLMs on five recommendation tasks, including rating prediction, sequential recommendation, direct recommendation, explanation generation, and review summarization. The benchmark results indicate that LLMs displayed only moderate proficiency in accuracy-based tasks such as sequential and direct recommendation.
  arXiv  Detail & Related papers  (2023-08-23T16:32:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.