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

arXiv: https://arxiv.org/abs/2610.19065 · HTML: https://mlsanity.com/paper/2610.19065/

## 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 (most cited first, 27 of 27)

- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020)
- [Transformer Memory as a Differentiable Search Index](https://mlsanity.com/paper/2202.06991/) (2022)
- [Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders](https://mlsanity.com/paper/2403.03952/) (2024)
- [Recommender Systems with Generative Retrieval](https://mlsanity.com/paper/2305.05065/) (2023)
- [Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations](https://mlsanity.com/paper/2402.17152/) (2024)
- [Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches](https://mlsanity.com/paper/1907.06902/) (2019)
- [Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation](https://mlsanity.com/paper/2311.09049/) (2023)
- [A Neural Corpus Indexer for Document Retrieval](https://mlsanity.com/paper/2206.02743/) (2022)
- [On the Theoretical Limitations of Embedding-Based Retrieval](https://mlsanity.com/paper/2508.21038/) (2025)
- [The Unfairness of Popularity Bias in Recommendation](https://mlsanity.com/paper/1907.13286/) (2019)
- [How Does Generative Retrieval Scale to Millions of Passages?](https://mlsanity.com/paper/2305.11841/) (2023)
- [A Survey on Popularity Bias in Recommender Systems](https://mlsanity.com/paper/2308.01118/) (2023)
- [A Critical Study on Data Leakage in Recommender System Offline Evaluation](https://mlsanity.com/paper/2010.11060/) (2020)
- [OneRec-V2 Technical Report](https://mlsanity.com/paper/2508.20900/) (2025)
- [A Case Study on Sampling Strategies for Evaluating Neural Sequential Item Recommendation Models](https://mlsanity.com/paper/2107.13045/) (2021)
- [OneRec Technical Report](https://mlsanity.com/paper/2506.13695/) (2025)
- [Widespread Flaws in Offline Evaluation of Recommender Systems](https://mlsanity.com/paper/2307.14951/) (2023)
- [Take a Fresh Look at Recommender Systems from an Evaluation Standpoint](https://mlsanity.com/paper/2210.04149/) (2022)
- [CRAB: Codebook Rebalancing for Bias Mitigation in Generative Recommendation](https://mlsanity.com/paper/2604.05113/) (2026)
- [Echoes in Filter Bubble: Diagnosing and Curing Popularity Bias in Generative Recommenders](https://mlsanity.com/paper/2605.16825/) (2026)
- [An Embarrassingly Simple Graph Heuristic Reveals Shortcut-Solvable Benchmarks for Sequential Recommendation](https://mlsanity.com/paper/2605.07125/) (2026)
- [T-RoPE: Time-Aware Rotary Position Embedding for Sequential Recommendation](https://mlsanity.com/paper/2609.30576/) (2026)

## 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.