# A Simple and Effective Framework for Symmetric Consistent Indexing in Large-Scale Dense Retrieval

arXiv: https://arxiv.org/abs/2512.13074 · HTML: https://mlsanity.com/paper/2512.13074/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 15 Dec 2025.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [Transformer Memory as a Differentiable Search Index](https://mlsanity.com/paper/2202.06991/) (2022)
- [Optimizing Dense Retrieval Model Training with Hard Negatives](https://mlsanity.com/paper/2104.08051/) (2021)
- [Learning Tree-based Deep Model for Recommender Systems](https://mlsanity.com/paper/1801.02294/) (2018)
- [A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques](https://mlsanity.com/paper/2106.14807/) (2021)
- [SimpleX: A Simple and Strong Baseline for Collaborative Filtering](https://mlsanity.com/paper/2109.12613/) (2021)
- [Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?](https://mlsanity.com/paper/2110.06918/) (2021)
- [T2Ranking: A large-scale Chinese Benchmark for Passage Ranking](https://mlsanity.com/paper/2304.03679/) (2023)
- [Distilling Dense Representations for Ranking using Tightly-Coupled Teachers](https://mlsanity.com/paper/2010.11386/) (2020)
- [Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance](https://mlsanity.com/paper/2108.00644/) (2021)
- [Ultron: An Ultimate Retriever on Corpus with a Model-based Indexer](https://mlsanity.com/paper/2208.09257/) (2022)
- [Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval](https://mlsanity.com/paper/2110.05789/) (2021)
- [Generative Retrieval via Term Set Generation](https://mlsanity.com/paper/2305.13859/) (2023)
- [Beyond Two-Tower Matching: Learning Sparse Retrievable Cross-Interactions for Recommendation](https://mlsanity.com/paper/2311.18213/) (2023)
- [Unleashing the Potential of Two-Tower Models: Diffusion-Based Cross-Interaction for Large-Scale Matching](https://mlsanity.com/paper/2502.20687/) (2025)

## Abstract (arXiv)

Dense retrieval has become the industry standard in large-scale information retrieval systems due to its high efficiency and competitive accuracy. Its core relies on a coarse-to-fine hierarchical architecture that enables rapid candidate selection and precise semantic matching, achieving millisecond-level response over billion-scale corpora. This capability makes it essential not only in traditional search and recommendation scenarios but also in the emerging paradigm of generative recommendation driven by large language models, where semantic IDs-themselves a form of coarse-to-fine representation-play a foundational role. However, the widely adopted dual-tower encoding architecture introduces inherent challenges, primarily representational space misalignment and retrieval index inconsistency, which degrade matching accuracy, retrieval stability, and performance on long-tail queries. These issues are further magnified in semantic ID generation, ultimately limiting the performance ceiling of downstream generative models. To address these challenges, this paper proposes a simple and effective framework named SCI comprising two synergistic modules: a symmetric representation alignment module that employs an innovative input-swapping mechanism to unify the dual-tower representation space without adding parameters, and an consistent indexing with dual-tower synergy module that redesigns retrieval paths using a dual-view indexing strategy to maintain consistency from training to inference. The framework is systematic, lightweight, and engineering-friendly, requiring minimal overhead while fully supporting billion-scale deployment. We provide theoretical guarantees for our approach, with its effectiveness validated by results across public datasets and real-world e-commerce datasets.