# TriSampler: A Better Negative Sampling Principle for Dense Retrieval

arXiv: https://arxiv.org/abs/2402.11855 · HTML: https://mlsanity.com/paper/2402.11855/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2024.

## Built on by (most cited first, 10 of 10)

- [Hard Negative Mining for Domain-Specific Retrieval in Enterprise Systems](https://mlsanity.com/paper/2505.18366/) (2025)
- [UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers](https://mlsanity.com/paper/2410.20163/) (2024)
- [BiCA: Effective Biomedical Dense Retrieval with Citation-Aware Hard Negatives](https://mlsanity.com/paper/2511.08029/) (2025)
- [MMGeoLM: Hard Negative Contrastive Learning for Fine-Grained Geometric Understanding in Large Multimodal Models](https://mlsanity.com/paper/2505.20152/) (2025)
- [Cross-Genre Authorship Attribution via LLM-Based Retrieve-and-Rerank](https://mlsanity.com/paper/2510.16819/) (2025)
- [RRRA: Resampling and Reranking through a Retriever Adapter](https://mlsanity.com/paper/2508.11670/) (2025)
- [Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment](https://mlsanity.com/paper/2511.08399/) (2025)
- [CroPS: Improving Dense Retrieval with Cross-Perspective Positive Samples in Short-Video Search](https://mlsanity.com/paper/2511.15443/) (2025)
- [What Tracks Hard-Negative Transfer? A Study of Lexical and Semantic Signals](https://mlsanity.com/paper/2603.20990/) (2026)
- [When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval](https://mlsanity.com/paper/2606.01304/) (2026)

## Abstract (arXiv)

Negative sampling stands as a pivotal technique in dense retrieval, essential for training effective retrieval models and significantly impacting retrieval performance. While existing negative sampling methods have made commendable progress by leveraging hard negatives, a comprehensive guiding principle for constructing negative candidates and designing negative sampling distributions is still lacking. To bridge this gap, we embark on a theoretical analysis of negative sampling in dense retrieval. This exploration culminates in the unveiling of the quasi-triangular principle, a novel framework that elucidates the triangular-like interplay between query, positive document, and negative document. Fueled by this guiding principle, we introduce TriSampler, a straightforward yet highly effective negative sampling method. The keypoint of TriSampler lies in its ability to selectively sample more informative negatives within a prescribed constrained region. Experimental evaluation show that TriSampler consistently attains superior retrieval performance across a diverse of representative retrieval models.