A Replicability Study of XTR

• URL: http://arxiv.org/abs/2605.00646v1
• Date: Fri, 01 May 2026 13:28:09 GMT
• Title: A Replicability Study of XTR
• Abstract summary: The original work proposes a modified training objective as necessary for effective XTR retrieval.<n>We replicate both the XTR retrieval algorithm and its modified training objective, and extend the evaluation to knowledge-distillation training and efficient retrieval engines.
• Score: 49.02573032242219
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The XTR (conteXtual Token Retrieval) algorithm is a modification to ColBERT retrieval that avoids the costly step of fully gathering and reranking the candidates' embeddings by imputing their missing similarity scores from the initial token retrieval step. The original work proposes a modified training objective as necessary for effective XTR retrieval, arguing that standard ColBERT token scoring is unsuitable for imputation. In this paper, we replicate both the XTR retrieval algorithm and its modified training objective, and extend the evaluation to knowledge-distillation (KD) training and efficient retrieval engines (PLAID and WARP). We confirm the token-level matching characteristics claimed in the original work, but fail to replicate XTR's overall effectiveness advantage over ColBERT under a controlled comparison. We further show that XTR's training modification has a concrete mechanistic consequence for modern retrieval engines: by flattening ColBERT's characteristically peaked token score distribution, XTR training yields more discriminative centroid scores and thus more efficient IVF-based retrieval under PLAID and WARP. The utility of XTR training is therefore not limited to the low-$k'$ regime originally studied, but extends to any deployment setting where IVF-based engines are used. These findings offer practitioners concrete guidance on how and when to use XTR as their multi-vector retriever.

Related papers

• OPSD Compresses What RLVR Teaches: A Post-RL Compaction Stage for Reasoning Models [12.17078443900398]
  On-Policy Self-Distillation (OPSD) has recently emerged as an alternative to Reinforcement Learning with Verifiable Rewards (RLVR)<n>We show that in thinking-enabled mathematical reasoning, OPSD behaves most reliably as a compression mechanism rather than a correction mechanism.
  arXiv  Detail & Related papers  (2026-05-07T13:04:34Z)
• Beyond Hungarian: Match-Free Supervision for End-to-End Object Detection [6.786987355161583]
  We propose a novel matching-free training scheme for DETR-based detectors.<n>We use encoded ground-truth information to probe the decoder queries through a cross-attention mechanism.<n> Experimental results demonstrate that our proposed method bypasses the traditional matching process.
  arXiv  Detail & Related papers  (2026-03-09T15:44:23Z)
• LaSeR: Reinforcement Learning with Last-Token Self-Rewarding [54.72617309922891]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a core paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs)<n>Previous practice requires the LLM to sequentially generate solutions and self-verifications using two separate prompt templates, which significantly reduces efficiency.<n>We propose LaSeR (Reinforcement Learning with Last-Token Self-Rewarding), an algorithm that simply augments the original RLVR loss with a MSE loss.
  arXiv  Detail & Related papers  (2025-10-16T17:55:11Z)
• WARP: An Efficient Engine for Multi-Vector Retrieval [42.128201454569165]
  WARP is a retrieval engine that substantially improves the efficiency of retrievers trained with the XTR objective.<n>Our system reduces end-to-end latency compared to XTR's reference implementation by 41x, and achieves a 3x speedup over the ColBERTv2/PLAID engine.
  arXiv  Detail & Related papers  (2025-01-29T17:26:47Z)
• Active Learning Framework for Cost-Effective TCR-Epitope Binding Affinity Prediction [6.3044887592852845]
  ActiveTCR is a framework that incorporates active learning and TCR-epitope binding affinity prediction models. It aims to maximize performance gains while minimizing the cost of annotation. Our work is the first systematic investigation of data optimization for TCR-epitope binding affinity prediction.
  arXiv  Detail & Related papers  (2023-10-16T23:53:07Z)
• Rank-DETR for High Quality Object Detection [52.82810762221516]
  A highly performant object detector requires accurate ranking for the bounding box predictions. In this work, we introduce a simple and highly performant DETR-based object detector by proposing a series of rank-oriented designs.
  arXiv  Detail & Related papers  (2023-10-13T04:48:32Z)
• Revisiting DETR Pre-training for Object Detection [24.372444866927538]
  We investigate the shortcomings of DETReg in enhancing the performance of robust DETR-based models under full data conditions. We employ an optimized approach named Simple Self-training which leads to marked enhancements through the combination of an improved box predictor and the Objects$365$ benchmark. The culmination of these endeavors results in a remarkable AP score of $59.3%$ on the COCO val set, outperforming $mathcalH$-Deformable-DETR + Swin-L without pre-training by $1.4%$.
  arXiv  Detail & Related papers  (2023-08-02T17:39:30Z)
• Aligned Unsupervised Pretraining of Object Detectors with Self-training [41.03780087924593]
  Unsupervised pretraining of object detectors has recently become a key component of object detector training. We propose a framework that mitigates this issue and consists of three simple yet key ingredients. We show that our strategy is also capable of pretraining from scratch (including the backbone) and works on complex images like COCO.
  arXiv  Detail & Related papers  (2023-07-28T17:46:00Z)
• Noise-Robust Dense Retrieval via Contrastive Alignment Post Training [89.29256833403167]
  Contrastive Alignment POst Training (CAPOT) is a highly efficient finetuning method that improves model robustness without requiring index regeneration. CAPOT enables robust retrieval by freezing the document encoder while the query encoder learns to align noisy queries with their unaltered root. We evaluate CAPOT noisy variants of MSMARCO, Natural Questions, and Trivia QA passage retrieval, finding CAPOT has a similar impact as data augmentation with none of its overhead.
  arXiv  Detail & Related papers  (2023-04-06T22:16:53Z)
• Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment [80.55064790937092]
  One-to-many assignment, assigning one ground-truth object to multiple predictions, succeeds in detection methods such as Faster R-CNN and FCOS. We introduce Group DETR, a simple yet efficient DETR training approach that introduces a group-wise way for one-to-many assignment. Experiments show that Group DETR significantly speeds up the training convergence and improves the performance of various DETR-based models.
  arXiv  Detail & Related papers  (2022-07-26T17:57:58Z)
• ReAct: Temporal Action Detection with Relational Queries [84.76646044604055]
  This work aims at advancing temporal action detection (TAD) using an encoder-decoder framework with action queries. We first propose a relational attention mechanism in the decoder, which guides the attention among queries based on their relations. Lastly, we propose to predict the localization quality of each action query at inference in order to distinguish high-quality queries.
  arXiv  Detail & Related papers  (2022-07-14T17:46:37Z)

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.