Advancing Relevance Measurement with Vision-Language Models for Web-Scale Search

• URL: http://arxiv.org/abs/2608.02446v1
• Date: Mon, 03 Aug 2026 16:23:49 GMT
• Title: Advancing Relevance Measurement with Vision-Language Models for Web-Scale Search
• Abstract summary: We present a VLM-based automated relevance evaluation pipeline deployed within Pinterest Search for online A/B experiments.<n>We rigorously validate the alignment between VLM-generated judgments and human annotations.<n>This approach leads to higher-quality relevance metrics and significantly reduces the Minimum Detectable Effects (MDEs) in online experiment measurements.
• Score: 5.210111523135908
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Relevance evaluation plays a crucial role in personalized search systems, serving as a guardrail alongside user engagement metrics to ensure that search results align with user queries and intent. While human annotation is the traditional method for relevance evaluation, its high cost and long turnaround time limit its scalability. In this work, we present a VLM-based automated relevance evaluation pipeline deployed within Pinterest Search for online A/B experiments. We rigorously validate the alignment between VLM-generated judgments and human annotations, demonstrating that VLMs can provide reliable relevance measurement for experiments while greatly improving the evaluation efficiency. Leveraging VLM-based labeling further unlocks opportunities to expand the query set, optimize sampling design, and efficiently assess a wider range of search experiences at scale. This approach leads to higher-quality relevance metrics and significantly reduces the Minimum Detectable Effects (MDEs) in online experiment measurements.

Related papers

• WebDevJudge: Evaluating (M)LLMs as Critiques for Web Development Quality [62.43165871914528]
  We introduce WebDevJudge, a systematic benchmark for assessing LLM-as-a-judge performance in web development.<n>WebDevJudge comprises human preference labels over paired web implementations, annotated with structured and query-grounded rubrics.<n>In-depth analysis indicates this gap stems from fundamental model limitations, including failures in recognizing functional equivalence, verifying task feasibility, and mitigating bias.
  arXiv  Detail & Related papers  (2025-10-21T12:16:04Z)
• Modernizing Facebook Scoped Search: Keyword and Embedding Hybrid Retrieval with LLM Evaluation [4.821105793289088]
  We introduce a framework of modernized Facebook Group Scoped Search.<n>We blend traditional keyword-based retrieval with embedding-based retrieval to improve the search relevance and diversity of search results.<n>Our results demonstrate that the blended retrieval system significantly enhances user engagement and search quality.
  arXiv  Detail & Related papers  (2025-09-17T00:22:08Z)
• LLM-based Relevance Assessment for Web-Scale Search Evaluation at Pinterest [3.306725465028306]
  We present our approach at Pinterest Search to automate relevance evaluation for online experiments using fine-tuned LLMs.<n>We rigorously validate the alignment between LLM-generated judgments and human annotations.<n>This approach leads to higher-quality relevance metrics and significantly reduces the Minimum Detectable Effect (MDE) in online experiment measurements.
  arXiv  Detail & Related papers  (2025-09-03T23:07:49Z)
• Exploring the Potential of LLMs for Serendipity Evaluation in Recommender Systems [10.227007419503297]
  Large language models (LLMs) are increasingly revolutionizing evaluation methodologies across various human annotation tasks.<n>We conduct a meta-evaluation on two datasets derived from real user studies in the e-commerce and movie domains.<n>Our findings indicate that even the simplest zero-shot LLMs achieve parity with, or surpass, the performance of conventional metrics.
  arXiv  Detail & Related papers  (2025-07-23T07:51:56Z)
• Leveraging LLMs to Evaluate Usefulness of Document [25.976948104719746]
  We introduce a new user-centric evaluation framework that integrates users' search context and behavioral data into large language models.<n>Our study demonstrates that when well-guided with context and behavioral information, LLMs can accurately evaluate usefulness.<n>We also apply the labels produced by our method to predict user satisfaction, with real-world experiments indicating that these labels substantially improve the performance of satisfaction prediction models.
  arXiv  Detail & Related papers  (2025-06-10T09:44:03Z)
• LLM-Driven Usefulness Judgment for Web Search Evaluation [12.10711284043516]
  Evaluation is fundamental in optimizing search experiences and supporting diverse user intents in Information Retrieval (IR)<n>Traditional search evaluation methods primarily rely on relevance labels, which assess how well retrieved documents match a user's query.<n>In this paper, we explore an alternative approach: LLM-generated usefulness labels, which incorporate both implicit and explicit user behavior signals to evaluate document usefulness.
  arXiv  Detail & Related papers  (2025-04-19T20:38:09Z)
• MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models [71.36392373876505]
  We introduce MMIE, a large-scale benchmark for evaluating interleaved multimodal comprehension and generation in Large Vision-Language Models (LVLMs)<n>MMIE comprises 20K meticulously curated multimodal queries, spanning 3 categories, 12 fields, and 102 subfields, including mathematics, coding, physics, literature, health, and arts.<n>It supports both interleaved inputs and outputs, offering a mix of multiple-choice and open-ended question formats to evaluate diverse competencies.
  arXiv  Detail & Related papers  (2024-10-14T04:15:00Z)
• Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators [48.54465599914978]
  Large Language Models (LLMs) have demonstrated promising capabilities as automatic evaluators in assessing the quality of generated natural language.<n>LLMs still exhibit biases in evaluation and often struggle to generate coherent evaluations that align with human assessments.<n>We introduce Pairwise-preference Search (PAIRS), an uncertainty-guided search-based rank aggregation method that employs LLMs to conduct pairwise comparisons locally and efficiently ranks candidate texts globally.
  arXiv  Detail & Related papers  (2024-03-25T17:11:28Z)
• Is Reference Necessary in the Evaluation of NLG Systems? When and Where? [58.52957222172377]
  We show that reference-free metrics exhibit a higher correlation with human judgment and greater sensitivity to deficiencies in language quality. Our study can provide insight into the appropriate application of automatic metrics and the impact of metric choice on evaluation performance.
  arXiv  Detail & Related papers  (2024-03-21T10:31:11Z)
• Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinement [79.2400720115588]
  We introduce Persona-DB, a simple yet effective framework consisting of a hierarchical construction process to improve generalization across task contexts.<n>In the evaluation of response prediction, Persona-DB demonstrates superior context efficiency in maintaining accuracy with a significantly reduced retrieval size.<n>Our experiments also indicate a marked improvement of over 10% under cold-start scenarios, when users have extremely sparse data.
  arXiv  Detail & Related papers  (2024-02-16T20:20:43Z)
• Exploring validation metrics for offline model-based optimisation with diffusion models [50.404829846182764]
  In model-based optimisation (MBO) we are interested in using machine learning to design candidates that maximise some measure of reward with respect to a black box function called the (ground truth) oracle. While an approximation to the ground oracle can be trained and used in place of it during model validation to measure the mean reward over generated candidates, the evaluation is approximate and vulnerable to adversarial examples. This is encapsulated under our proposed evaluation framework which is also designed to measure extrapolation.
  arXiv  Detail & Related papers  (2022-11-19T16:57:37Z)

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.