Lune

ACL Findings2026

Distilling LLM Reasoning into Dense Encoders: Bridging the Accuracy-Efficiency Gap in Recommendation

Donghee Han, Daeyoung Roh, A Young Kim, Hwanjun Song, Mun Yong Yi

Abstract

Large Language Models (LLMs) have shown remarkable potential in recommendation systems but suffer from prohibitive inference latency. Existing distillation approaches typically target Small Language Models (SLMs) or Conventional Recommendation Models (CRMs), yet face a critical trade-off between computational cost and semantic reasoning capacity. To bridge this accuracy-efficiency gap, we introduce Reasoning-to-Encoder Distillation (R2END), a framework that establishes a text encoder as the optimal student architecture for scalable recommendation. Unlike methods that mimic token generation, R2END compresses the teacher's reasoning into a dense vector space via a semantic alignment objective, effectively capturing user-item dynamics. Extensive experiments on four datasets demonstrate that R2END not only outperforms stateof-the-art baselines but also achieves drastically reduced latency, offering a sweet spot for recommendation.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation cites Representation Learning with Large Language Models for Recommendation
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on23

  1. Recommender Systems with Generative RetrievalShashank Rajput, Nikhil Mehta, Anima Singh, Raghunandan Hulikal Keshavan et al.NeurIPS 2023 · 474 citations
  2. Representation Learning with Large Language Models for RecommendationXubin Ren, Wei Wei, Lianghao Xia, Lixin Su et al.WWW 2024 · 385 citations
  3. LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential RecommendationQidong Liu, Xian Wu, Yejing Wang, Zijian Zhang et al.NeurIPS 2024 · 154 citations
  4. Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender SystemSein Kim, Hongseok Kang, Seungyoon Choi, Donghyun Kim et al.KDD 2024 · 107 citations
  5. MiniLLM: Knowledge Distillation of Large Language ModelsYuxian Gu, Li Dong, Furu Wei, Minlie HuangICLR 2024 · 95 citations

Related papers

  1. Think, But Don't Tell: Implicit Reasoning for LLM-based Sequential Recommendation via Multi-Teacher DistillationWeihai Lu, Xiaoxi Cui, Chenke YinSIGIR 2026
  2. From Prediction to Understanding: Leveraging Reasoning in Large Language Model-based RecommendationsZhi-Yuan Chen, Siyu Lu, Qiang Liu, Xingxing Wang et al.WWW 2026
  3. Semantic Convergence: Harmonizing Recommender Systems via Two-Stage Alignment and Behavioral Semantic TokenizationGuanghan Li, Xun Zhang, Yufei Zhang, Yifan Yin et al.AAAI 2025 · 18 citations
  4. Review-driven Personalized Preference Reasoning with Large Language Models for RecommendationJieyong Kim, Hyunseo Kim, Hyunjin Cho, SeongKu Kang et al.SIGIR 2025 · 13 citations
  5. Think before Recommendation: Autonomous Reasoning-enhanced RecommenderXiaoyu Kong, Junguang Jiang, Bin Liu, Ziru Xu et al.NeurIPS 2025 · 17 citations
Dusk over the sea between two cliffs drawn in fine vertical lines