Test-Time Training for Zero-Resource Dense Retrieval Reranking

• URL: http://arxiv.org/abs/2606.01070v1
• Date: Sun, 31 May 2026 07:26:40 GMT
• Title: Test-Time Training for Zero-Resource Dense Retrieval Reranking
• Abstract summary: Existing approaches face a fundamental dilemma: cross-encoders deliver strong reranking quality but require costly supervised training and incur high latency.<n>We propose DART (Dense Adaptive Reranking at Test-time), which resolves this dilemma by adapting the scoring function at inference time.<n>On six BEIR benchmarks, DART achieves a mean per-dataset relative NDCG@10 gain of +2.1% over the dense retrieval baseline with under 10ms additional latency per query.
• Score: 3.498051445282382
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Dense retrievers excel at first-stage candidate generation but lack effective reranking in zero-resource settings. Existing approaches face a fundamental dilemma: cross-encoders deliver strong reranking quality but require costly supervised training and incur high latency, while unsupervised BM25 reranking consistently degrades dense retrieval performance on most of BEIR benchmarks. We propose DART (Dense Adaptive Reranking at Test-time), which resolves this dilemma by adapting the scoring function at inference time. For each query, the top-ranked documents serve as pseudo-positive examples and the bottom-ranked as pseudo-negative examples, providing noisy but readily available supervision to adapt a bilinear scoring matrix $W$ via a small number of gradient updates. We further introduce a confidence-weighted margin loss and a cross-query momentum buffer that warm-starts adaptation across queries. On six BEIR benchmarks, DART achieves a mean per-dataset relative NDCG@10 gain of +2.1% over the dense retrieval baseline with under 10ms additional latency per query, demonstrating a powerful capability for zero-shot performance enhancement and cross-domain generalization.

Related papers

• Adaptive Re-Ranking [9.210588331263503]
  We propose Adaptive Re-Ranking, a utility-based labeling framework for cost-aware routing.<n>We train a routing classifier with 3 strategies: sparse retrieval (BM25), dense re-ranking (MiniLM-L6-v2), and heavy neural re-ranking (BGE-v2-m3)<n>Compared to BGE our method achieves 1.15-53x lower median latency and 1.11-5.22x lower mean latency across all datasets we have tested, while delivering -17.5% to +4.0% nDCG@10.
  arXiv  Detail & Related papers  (2026-06-24T00:12:44Z)
• OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework [30.771327347534996]
  OrderDP aims to obtain stable, unbiased, and near-lossless training acceleration with theoretical guarantees.<n>We evaluate OrderDP against comprehensive baselines on CIFAR-10, CIFAR-100, and ImageNet-1K.
  arXiv  Detail & Related papers  (2026-06-07T11:11:51Z)
• Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overhead [20.897837226246367]
  We reproduce a reasoning-intensive retrieval benchmark (BRIGHT) across 12 tasks and 14 retrievers.<n>We extend evaluation with cold-start indexing cost, query latency distributions and throughput.<n>We find that some reasoning-specialized retrievers achieve strong effectiveness while remaining competitive in throughput.
  arXiv  Detail & Related papers  (2026-04-04T10:24:19Z)
• OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation [39.548179971747906]
  Domain-specific finetuning is essential for dense retrievers, yet not all training pairs contribute equally to the learning process.<n>We introduce OPERA, a data pruning framework that exploits this heterogeneity to improve both the effectiveness and efficiency of retrieval model adaptation.
  arXiv  Detail & Related papers  (2026-03-17T23:11:45Z)
• Robust Test-time Video-Text Retrieval: Benchmarking and Adapting for Query Shifts [28.52079785516312]
  Video-text retrieval (VTR) models are highly vulnerable to real-world query shifts.<n>We propose HAT-VTR (Hubness Alleviation for Test-time Video-Text Retrieval), as our baseline test-time adaptation framework.<n>Extensive experiments demonstrate that HAT-VTR substantially improves robustness, consistently outperforming methods across diverse query shift scenarios.
  arXiv  Detail & Related papers  (2026-02-15T05:57:44Z)
• CVeDRL: An Efficient Code Verifier via Difficulty-aware Reinforcement Learning [57.24524263804788]
  Code verifiers play a critical role in post-verification for LLM-based code generation.<n>Existing supervised fine-tuning methods suffer from data scarcity, high failure rates, and poor inference efficiency.<n>We show that naive RL with only functionality rewards fails to generate effective unit tests for difficult branches and samples.
  arXiv  Detail & Related papers  (2026-01-30T10:33:29Z)
• Towards High Data Efficiency in Reinforcement Learning with Verifiable Reward [54.708851958671794]
  We propose a Data-Efficient Policy Optimization pipeline that combines optimized strategies for both offline and online data selection.<n>In offline phase, we curate a high-quality subset of training samples based on diversity, influence, and appropriate difficulty.<n>During online RLVR training, we introduce a sample-level explorability metric to dynamically filter samples with low exploration potential.
  arXiv  Detail & Related papers  (2025-09-01T10:04:20Z)
• ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning [72.05731026796335]
  Multi-turn dialogue systems often suffer from degraded performance when exposed to low-quality data.<n>We propose ReSURE, an adaptive learning method that dynamically down-weights unreliable supervision without explicit filtering.<n>Experiments on both single-source and mixed-quality datasets show improved stability and response quality.
  arXiv  Detail & Related papers  (2025-08-27T15:54:01Z)
• RADAR: Recall Augmentation through Deferred Asynchronous Retrieval [0.0]
  We introduce Recall Augmentation through Deferred Asynchronous Retrieval (RADAR)<n>RADAR pre-ranks a significantly larger candidate set for users using the full complexity ranking model.<n>RADAR significantly boosts recall by effectively combining a larger retrieved candidate set with a more powerful ranking model.
  arXiv  Detail & Related papers  (2025-06-08T19:21:46Z)
• Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval [49.669503570350166]
  Generative information retrieval (GenIR) is a promising neural retrieval paradigm that formulates document retrieval as a document identifier (docid) generation task.<n>Existing GenIR models suffer from token-level misalignment, where models trained to predict the next token often fail to capture document-level relevance effectively.<n>We propose direct document relevance optimization (DDRO), which aligns token-level docid generation with document-level relevance estimation through direct optimization via pairwise ranking.
  arXiv  Detail & Related papers  (2025-04-07T15:27:37Z)
• Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization [67.8738082040299]
  Self-Sampling Preference Optimization (SSPO) is a new alignment method for post-training reinforcement learning.<n>SSPO eliminates the need for paired data and reward models while retaining the training stability of SFT.<n>SSPO surpasses all previous approaches on the text-to-image benchmarks and demonstrates outstanding performance on the text-to-video benchmarks.
  arXiv  Detail & Related papers  (2024-10-07T17:56:53Z)
• Revisiting BPR: A Replicability Study of a Common Recommender System Baseline [78.00363373925758]
  We study the features of the BPR model, indicating their impact on its performance, and investigate open-source BPR implementations. Our analysis reveals inconsistencies between these implementations and the original BPR paper, leading to a significant decrease in performance of up to 50% for specific implementations. We show that the BPR model can achieve performance levels close to state-of-the-art methods on the top-n recommendation tasks and even outperform them on specific datasets.
  arXiv  Detail & Related papers  (2024-09-21T18:39:53Z)

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.