Real-Time Hard Negative Sampling via LLM-based Clustering for Large-Scale Two-Tower Retrieval

• URL: http://arxiv.org/abs/2607.00448v2
• Date: Mon, 06 Jul 2026 17:02:14 GMT
• Title: Real-Time Hard Negative Sampling via LLM-based Clustering for Large-Scale Two-Tower Retrieval
• Abstract summary: Two-tower model has been widely used for large-scale recommendation systems.<n>Industry standards for training two-tower models typically involve in-batch and/or out-of-batch negative sampling.<n>A novel self-supervised hard negative sampling technique is proposed that leverages a large language model.
• Score: 6.945551949047715
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The two-tower model has been widely used for large-scale recommendation systems, particularly in the retrieval stage. Industry standards for training two-tower models typically involve in-batch and/or out-of-batch negative sampling. However, these methods often produce easy negatives that models can quickly learn, failing to sufficiently challenge the model. To address this issue, a novel self-supervised hard negative sampling technique is proposed that leverages a large language model (LLM) to generate hard negatives from the same cluster during model training. By utilizing the LLM to learn media representations, the proposed approach ensures that the generated negatives are more challenging and informative. This real-time sampling framework is designed for seamless integration into production models, capable of handling billions of training data points with minimal computational complexity. Experiments on public datasets, along with deployment to a large-scale online system, demonstrate that the proposed negative sampling technique outperforms widely used industry methods. Furthermore, analysis in industrial applications reveals that this sampling method can help break inherent feedback loops in recommendations and significantly reduce popularity bias.

Related papers

• Improving LLM-based Recommendation with Self-Hard Negatives from Intermediate Layers [80.55429742713623]
  ILRec is a novel preference fine-tuning framework for LLM-based recommender systems.<n>We introduce a lightweight collaborative filtering model to assign token-level rewards for negative signals.<n>Experiments on three datasets demonstrate ILRec's effectiveness in enhancing the performance of LLM-based recommender systems.
  arXiv  Detail & Related papers  (2026-02-19T14:37:43Z)
• Reasoning with Sampling: Your Base Model is Smarter Than You Think [52.639108524651846]
  We propose a simple iterative sampling algorithm leveraging the base models' own likelihoods.<n>We show that our algorithm offers substantial boosts in reasoning that nearly match and even outperform those from RL.<n>Our method does not require training, curated datasets, or a verifier.
  arXiv  Detail & Related papers  (2025-10-16T17:18:11Z)
• Enhancing User Sequence Modeling through Barlow Twins-based Self-Supervised Learning [17.299357794051797]
  We propose an adaptation of Barlow Twins, a state-of-the-art SSL methods, to user sequence modeling by incorporating suitable augmentation methods.<n>Our approach aims to mitigate the need for large negative sample batches, enabling effective representation learning with smaller batch sizes and limited labeled data.
  arXiv  Detail & Related papers  (2025-05-02T02:04:52Z)
• Can LLM-Driven Hard Negative Sampling Empower Collaborative Filtering? Findings and Potentials [9.668242919588199]
  Hard negative samples can accelerate model convergence and optimize decision boundaries.<n>This paper introduces the concept of Semantic Negative Sampling.<n>We propose a framework called HNLMRec, based on fine-tuning LLMs supervised by collaborative signals.
  arXiv  Detail & Related papers  (2025-04-07T04:39:45Z)
• SyNeg: LLM-Driven Synthetic Hard-Negatives for Dense Retrieval [45.971786380884126]
  The performance of Dense retrieval (DR) is significantly influenced by the quality of negative sampling.<n>Recent advancements in large language models (LLMs) offer an innovative solution by generating contextually rich and diverse negative samples.<n>In this work, we present a framework that harnesses LLMs to synthesize high-quality hard negative samples.
  arXiv  Detail & Related papers  (2024-12-23T03:49:00Z)
• Rethinking negative sampling in content-based news recommendation [1.5416095780642964]
  News recommender systems are hindered by the brief lifespan of articles, as they undergo rapid relevance decay. Recent studies have demonstrated the potential of content-based neural techniques in tackling this problem. In this study, we posit that the careful sampling of negative examples has a big impact on the model's outcome.
  arXiv  Detail & Related papers  (2024-11-13T15:42:13Z)
• Enhancing Retrieval Performance: An Ensemble Approach For Hard Negative Mining [0.0]
  This study focuses on explaining the crucial role of hard negatives in the training process of cross-encoder models. We have developed a robust hard negative mining technique for efficient training of cross-encoder re-rank models on an enterprise dataset.
  arXiv  Detail & Related papers  (2024-10-18T05:23:39Z)
• Generating Negative Samples for Sequential Recommendation [83.60655196391855]
  We propose to Generate Negative Samples (items) for Sequential Recommendation (SR) A negative item is sampled at each time step based on the current SR model's learned user preferences toward items. Experiments on four public datasets verify the importance of providing high-quality negative samples for SR.
  arXiv  Detail & Related papers  (2022-08-07T05:44:13Z)
• Rethinking Collaborative Metric Learning: Toward an Efficient Alternative without Negative Sampling [156.7248383178991]
  Collaborative Metric Learning (CML) paradigm has aroused wide interest in the area of recommendation systems (RS) We find that negative sampling would lead to a biased estimation of the generalization error. Motivated by this, we propose an efficient alternative without negative sampling for CML named textitSampling-Free Collaborative Metric Learning (SFCML)
  arXiv  Detail & Related papers  (2022-06-23T08:50:22Z)
• Low-variance estimation in the Plackett-Luce model via quasi-Monte Carlo sampling [58.14878401145309]
  We develop a novel approach to producing more sample-efficient estimators of expectations in the PL model. We illustrate our findings both theoretically and empirically using real-world recommendation data from Amazon Music and the Yahoo learning-to-rank challenge.
  arXiv  Detail & Related papers  (2022-05-12T11:15:47Z)
• Rethinking InfoNCE: How Many Negative Samples Do You Need? [54.146208195806636]
  We study how many negative samples are optimal for InfoNCE in different scenarios via a semi-quantitative theoretical framework. We estimate the optimal negative sampling ratio using the $K$ value that maximizes the training effectiveness function.
  arXiv  Detail & Related papers  (2021-05-27T08:38:29Z)
• Reinforced Negative Sampling over Knowledge Graph for Recommendation [106.07209348727564]
  We develop a new negative sampling model, Knowledge Graph Policy Network (kgPolicy), which works as a reinforcement learning agent to explore high-quality negatives. kgPolicy navigates from the target positive interaction, adaptively receives knowledge-aware negative signals, and ultimately yields a potential negative item to train the recommender.
  arXiv  Detail & Related papers  (2020-03-12T12:44:30Z)

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.