Mapping Similarity Spaces across Embedding Models with Synthetic Query Probing

• URL: http://arxiv.org/abs/2608.05857v1
• Date: Thu, 06 Aug 2026 10:38:13 GMT
• Title: Mapping Similarity Spaces across Embedding Models with Synthetic Query Probing
• Abstract summary: We study how similarity scores can be related by learning mappings between score distributions rather than embeddings.<n>We introduce Synthetic Query Probing, generating queries from documents to create controlled query-chunk pairs.<n>Experiments on SciFact and a proprietary corpus show that while models largely agree on rankings, their absolute scores exhibit systematic distortions.
• Score: 0.18006769874322107
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Retrieval-Augmented Generation systems rely on similarity scores to retrieve relevant content, yet scores are not directly comparable across embedding models due to differing geometric properties, complicating model migration and limiting threshold reuse. We study how similarity scores can be related by learning mappings between score distributions rather than embeddings. We introduce Synthetic Query Probing, generating queries from documents to create controlled query-chunk pairs, enabling large-scale, reference-free analysis of cross-model similarity behavior. We evaluate the approach on multiple embedding configurations and learn score conversion functions using linear, isotonic, and quantile mappings. Experiments on SciFact and a proprietary corpus show that while models largely agree on rankings, their absolute scores exhibit systematic distortions. Learned mappings partially align these spaces and improve threshold portability, with isotonic regression performing best. Our results highlight the need for cross-model calibration and position Synthetic Query Probing as a scalable framework for analyzing embedding comparability.

Related papers

• End-to-End Cell Detection via Instance-aware Graph Modeling [31.98156719497261]
  We propose an end-to-end framework for cell detection and classification.<n>It incorporates a dynamic graph construction module and an instance-aware graph network.<n>Our method significantly outperforms existing approaches in both detection and classification performance.
  arXiv  Detail & Related papers  (2026-09-14T10:37:19Z)
• ABLE: Representing and Mapping LLMs via Attribution-Based Large-model Embedding [23.27523995613204]
  We propose ABLE (Attribution-Based Large-model Embedding), a framework that leverages the interpretability space to construct model representations.<n>By aggregating gradient-based feature attributions via a tokenizer-agnostic word-level alignment, ABLE captures model-specific input-sensitivity patterns.<n>Our training-free approach achieves competitive or superior performance in relation prediction, model routing, and benchmark score prediction.
  arXiv  Detail & Related papers  (2026-04-20T04:55:11Z)
• Nonparametric Data Attribution for Diffusion Models [57.820618036556084]
  Data attribution for generative models seeks to quantify the influence of individual training examples on model outputs.<n>We propose a nonparametric attribution method that operates entirely on data, measuring influence via patch-level similarity between generated and training images.
  arXiv  Detail & Related papers  (2025-10-16T03:37:16Z)
• Model Correlation Detection via Random Selection Probing [62.093777777813756]
  Existing similarity-based methods require access to model parameters or produce scores without thresholds.<n>We introduce Random Selection Probing (RSP), a hypothesis-testing framework that formulates model correlation detection as a statistical test.<n>RSP produces rigorous p-values that quantify evidence of correlation.
  arXiv  Detail & Related papers  (2025-09-29T01:40:26Z)
• DDB: Diffusion Driven Balancing to Address Spurious Correlations [24.940576844328408]
  Deep neural networks trained with Empirical Risk Minimization often fail to generalize to out-of-distribution samples.<n>We propose a Diffusion Driven Balancing (DDB) technique to generate training samples with text-to-image diffusion models.<n>Our experiments show that our technique achieves better worst-group accuracy than the existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-21T15:28:22Z)
• Beyond Benchmarks: Evaluating Embedding Model Similarity for Retrieval Augmented Generation Systems [0.9976432338233169]
  We evaluate the similarity of embedding models within the context of RAG systems. We compare different families of embedding models, including proprietary ones, across five datasets. We identify possible open-source alternatives to proprietary models, with Mistral exhibiting the highest similarity to OpenAI models.
  arXiv  Detail & Related papers  (2024-07-11T08:24:16Z)
• Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling [82.36856860383291]
  We demonstrate that accurate estimation of the score function is achievable by training a standard deep ReLU neural network. We establish bounds on the error rate of recovering causal relationships using the score-matching-based causal discovery method.
  arXiv  Detail & Related papers  (2023-10-27T13:09:56Z)
• Revisiting the Evaluation of Image Synthesis with GANs [55.72247435112475]
  This study presents an empirical investigation into the evaluation of synthesis performance, with generative adversarial networks (GANs) as a representative of generative models. In particular, we make in-depth analyses of various factors, including how to represent a data point in the representation space, how to calculate a fair distance using selected samples, and how many instances to use from each set.
  arXiv  Detail & Related papers  (2023-04-04T17:54:32Z)
• Smoothed Embeddings for Certified Few-Shot Learning [63.68667303948808]
  We extend randomized smoothing to few-shot learning models that map inputs to normalized embeddings. Our results are confirmed by experiments on different datasets.
  arXiv  Detail & Related papers  (2022-02-02T18:19:04Z)
• Cluster Analysis of a Symbolic Regression Search Space [2.055204980188575]
  We take a closer look at the distribution of symbolic regression models generated by genetic programming in the search space. We identify unique models and cluster them based on phenotypic as well as genotypic similarity. By mapping solution candidates visited by GP to the enumerated search space we find that GP initially explores the whole search space and later converges to the subspace of highest quality expressions.
  arXiv  Detail & Related papers  (2021-09-28T17:50:29Z)
• Robust Finite Mixture Regression for Heterogeneous Targets [70.19798470463378]
  We propose an FMR model that finds sample clusters and jointly models multiple incomplete mixed-type targets simultaneously. We provide non-asymptotic oracle performance bounds for our model under a high-dimensional learning framework. The results show that our model can achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-10-12T03:27:07Z)
• Out-of-distribution Generalization via Partial Feature Decorrelation [72.96261704851683]
  We present a novel Partial Feature Decorrelation Learning (PFDL) algorithm, which jointly optimize a feature decomposition network and the target image classification model. The experiments on real-world datasets demonstrate that our method can improve the backbone model's accuracy on OOD image classification datasets.
  arXiv  Detail & Related papers  (2020-07-30T05:48:48Z)
• Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework [31.35912529064612]
  We re-implemented and evaluated 21 interaction models in the PyKEEN software package. We performed a large-scale benchmarking on four datasets with several thousands of experiments and 24,804 GPU hours of time.
  arXiv  Detail & Related papers  (2020-06-23T22:30:52Z)

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.