mlsanityData to 14 Oct 2026

Revisiting Generative vs. Dense Retrieval: A Static Value Prior Reverses the Gap

arXiv 2610.19065 ↗First posted 13 Oct 2026cs.IR cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Generative retrieval (GR) has emerged as a strong candidate generator for sequential recommendation as language models and semantic-item identifiers have improved. However, GR is not a uniformly stronger replacement of dense retrieval (DR) in online retail candidate generation. We examine their differences on two Amazon Toys datasets under different metrics. GR leads on best relevant item value among users both methods cover, while DR leads on exact-target recall and relevant value across the ranked list. With deep analysis, we find that popularity contributes the most to GR's measured value lead. Adding the same static item value to DR in one reranking step reverses this lead and keeps recall above GR. Finally, on an industrial-scale internal e-commerce dataset with LLM-judged relevance, we show that a 14B SID-LLM still underperforms a 47× smaller dense encoder.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 40 references that are in the map. First posted on arXiv 13 Oct 2026.

Builds on

27 of 40 references.

References · 27

  1. 2018Self-Attentive Sequential Recommendationcited by 1,184
  2. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 964
  3. 2015Session-based Recommendations with Recurrent Neural Networkscited by 695
  4. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 520
  5. 2022Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)cited by 402
  6. 2020Autoregressive Entity Retrievalcited by 334
  7. 2022Transformer Memory as a Differentiable Search Indexcited by 247
  8. 2024Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoderscited by 224
  9. 2023Recommender Systems with Generative Retrievalcited by 198
  10. 2024Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendationscited by 188
  11. 2019Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approachescited by 185
  12. 2023Adapting Large Language Models by Integrating Collaborative Semantics for Recommendationcited by 179
15 more
  1. 2022A Neural Corpus Indexer for Document Retrievalcited by 111
  2. 2025On the Theoretical Limitations of Embedding-Based Retrievalcited by 104
  3. 2019The Unfairness of Popularity Bias in Recommendationcited by 70
  4. 2023How Does Generative Retrieval Scale to Millions of Passages?cited by 48
  5. 2023A Survey on Popularity Bias in Recommender Systemscited by 43
  6. 2020A Critical Study on Data Leakage in Recommender System Offline Evaluationcited by 39
  7. 2025OneRec-V2 Technical Reportcited by 29
  8. 2021A Case Study on Sampling Strategies for Evaluating Neural Sequential Item Recommendation Modelscited by 25
  9. 2025OneRec Technical Reportcited by 25
  10. 2023Widespread Flaws in Offline Evaluation of Recommender Systemscited by 22
  11. 2022Take a Fresh Look at Recommender Systems from an Evaluation Standpointcited by 17
  12. 2026CRAB: Codebook Rebalancing for Bias Mitigation in Generative Recommendationcited by 5
  13. 2026Echoes in Filter Bubble: Diagnosing and Curing Popularity Bias in Generative Recommenderscited by 2
  14. 2026An Embarrassingly Simple Graph Heuristic Reveals Shortcut-Solvable Benchmarks for Sequential Recommendationcited by 1
  15. 2026T-RoPE: Time-Aware Rotary Position Embedding for Sequential Recommendationcited by 1

Built on by

Not cited yet.