WSDM Cup 2026 Multilingual Retrieval: A Low-Cost Multi-Stage Retrieval Pipeline

• URL: http://arxiv.org/abs/2602.16989v1
• Date: Thu, 19 Feb 2026 01:28:18 GMT
• Title: WSDM Cup 2026 Multilingual Retrieval: A Low-Cost Multi-Stage Retrieval Pipeline
• Abstract summary: We present a low-cost retrieval system for the WSDM Cup 2026 multilingual retrieval task.<n>English queries are used to retrieve relevant documents from a collection of approximately ten million news articles in Chinese, Persian, and Russian.
• Score: 0.6445605125467574
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a low-cost retrieval system for the WSDM Cup 2026 multilingual retrieval task, where English queries are used to retrieve relevant documents from a collection of approximately ten million news articles in Chinese, Persian, and Russian, and to output the top-1000 ranked results for each query. We follow a four-stage pipeline that combines LLM-based GRF-style query expansion with BM25 candidate retrieval, dense ranking using long-text representations from jina-embeddings-v4, and pointwise re-ranking of the top-20 candidates using Qwen3-Reranker-4B while preserving the dense order for the remaining results. On the official evaluation, the system achieves nDCG@20 of 0.403 and Judged@20 of 0.95. We further conduct extensive ablation experiments to quantify the contribution of each stage and to analyze the effectiveness of query expansion, dense ranking, and top-$k$ reranking under limited compute budgets.

Related papers

• IGT @ FinMMEval 2026 Task 2: Question-Type Prompting with Targeted Extraction for Multilingual Financial QA [0.0]
  PolyFiQA Task 2 was a multilingual financial question answering task over English SEC filings and multilingual news articles.<n>Our central observation is that the 344 development questions divide into two families requiring fundamentally different approaches.<n>A dataset analysis reveals that 17-18 of 19 ground-truth reference answers per synthesis type share an exact evidence label prefix.<n>The final system achieves development ROUGE-1 approximately 0.395, a 60% relative improvement over a generic RAG baseline.
  arXiv  Detail & Related papers  (2026-09-08T02:23:31Z)
• Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn RAG [2.9721401411878254]
  Multi-turn retrieval-augmented generation (RAG) is challenging due to evolving user intent, conversational noise, and strict context limits.<n>We propose a training-free hybrid retrieval pipeline for SemEval-2026 Task 8 that combines dense and sparse retrieval with controlled query rewriting and cross-encoder reranking.
  arXiv  Detail & Related papers  (2026-06-05T07:28:01Z)
• Evaluation of Chunking Strategies for Effective Text Embedding in Low-Resource Language on Agricultural Documents [0.0]
  Performance is evaluated using four metrics: Average Retrieval Score (L2 distance), Answer Relevance, Khmer Coverage, and Khmer Intersection over Union.<n>We observe the best performance for the character-based Recursive chunking method with a chunk size of 300 characters.
  arXiv  Detail & Related papers  (2026-05-21T09:06:13Z)
• From BM25 to Corrective RAG: Benchmarking Retrieval Strategies for Text-and-Table Documents [0.0]
  We benchmark ten retrieval strategies spanning sparse, dense, hybrid fusion, cross-encoder reranking, query expansion, index augmentation, and adaptive retrieval.<n>We evaluate retrieval quality via Recall@k, MRR, and nDCG, and end-to-end generation quality via Number Match.
  arXiv  Detail & Related papers  (2026-04-02T07:53:40Z)
• Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage [89.58253972744531]
  Retrieval-augmented generation (RAG) systems combine document retrieval with a generative model to address complex information seeking tasks like report generation.<n>We investigate whether upstream retrieval metrics can serve as reliable early indicators of the final generated response's information coverage.<n>Our findings demonstrate strong correlations between coverage-based retrieval metrics and nugget coverage in generated responses at both topic and system levels.
  arXiv  Detail & Related papers  (2026-03-09T18:20:20Z)
• SAGE: Benchmarking and Improving Retrieval for Deep Research Agents [60.53966065867568]
  We introduce SAGE, a benchmark for scientific literature retrieval comprising 1,200 queries across four scientific domains, with a 200,000 paper retrieval corpus.<n>We evaluate six deep research agents and find that all systems struggle with reasoning-intensive retrieval.<n> BM25 significantly outperforms LLM-based retrievers by approximately 30%, as existing agents generate keyword-oriented sub-queries.
  arXiv  Detail & Related papers  (2026-02-05T18:25:24Z)
• Towards Global Retrieval Augmented Generation: A Benchmark for Corpus-Level Reasoning [50.27838512822097]
  We introduce GlobalQA, the first benchmark specifically designed to evaluate global RAG capabilities.<n>We propose GlobalRAG, a multi-tool collaborative framework that preserves structural coherence through chunk-level retrieval.<n>On the Qwen2.5-14B model, GlobalRAG achieves 6.63 F1 compared to the strongest baseline's 1.51 F1.
  arXiv  Detail & Related papers  (2025-10-30T07:29:14Z)
• AKCIT-FN at CheckThat! 2025: Switching Fine-Tuned SLMs and LLM Prompting for Multilingual Claim Normalization [0.5274891943689054]
  Claim normalization is a crucial step in automated fact-checking pipelines.<n>This paper details our submission to the CLEF-2025 CheckThat! Task2, which challenges systems to perform claim normalization across twenty languages.
  arXiv  Detail & Related papers  (2025-09-15T01:19:49Z)
• InsertRank: LLMs can reason over BM25 scores to Improve Listwise Reranking [3.1125398490785217]
  InsertRank is an LLM-based reranker that leverages lexical signals like BM25 scores during reranking to further improve retrieval performance.<n>With Deepseek-R1, InsertRank achieves a score of 37.5 on the BRIGHT benchmark, and 51.1 on the R2MED benchmark, surpassing previous methods.
  arXiv  Detail & Related papers  (2025-06-17T01:04:45Z)
• Deep Retrieval at CheckThat! 2025: Identifying Scientific Papers from Implicit Social Media Mentions via Hybrid Retrieval and Re-Ranking [4.275139302875217]
  We present the methodology and results of the Deep Retrieval team for subtask 4b of the CLEF CheckThat! 2025 competition.<n>We propose a hybrid retrieval pipeline that combines lexical precision, semantic generalization, and deep contextual re-ranking.<n>Our approach achieves a mean reciprocal rank at 5 (MRR@5) of 76.46% on the development set and 66.43% on the hidden test set.
  arXiv  Detail & Related papers  (2025-05-29T08:55:39Z)
• WebFAQ: A Multilingual Collection of Natural Q&A Datasets for Dense Retrieval [0.8478469524684645]
  WebFAQ is a large-scale collection of open-domain question answering datasets derived from FAQ-style schema.org annotations.<n>In total, the data collection consists of 96 million natural question-answer (QA) pairs across 75 languages, including 47 million (49%) non-English samples.<n>WebFAQ serves as the foundation for 20 monolingual retrieval benchmarks with a total size of 11.2 million QA pairs.
  arXiv  Detail & Related papers  (2025-02-28T10:46:52Z)
• BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval [54.54576644403115]
  We introduce BRIGHT, the first text retrieval benchmark that requires intensive reasoning to retrieve relevant documents.<n>Our dataset consists of 1,384 real-world queries spanning diverse domains, such as economics, psychology, mathematics, and coding.<n>We show that incorporating explicit reasoning about the query improves retrieval performance by up to 12.2 points.
  arXiv  Detail & Related papers  (2024-07-16T17:58:27Z)
• Generative Relevance Feedback and Convergence of Adaptive Re-Ranking: University of Glasgow Terrier Team at TREC DL 2023 [20.95345024616033]
  This paper describes our participation in the TREC 2023 Deep Learning Track. We submitted runs that apply generative relevance feedback from a large language model in both a zero-shot and pseudo-relevance feedback setting. We find some performance gains from the application of generative query reformulation.
  arXiv  Detail & Related papers  (2024-05-02T09:36:00Z)
• Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting [65.00288634420812]
  Pairwise Ranking Prompting (PRP) is a technique to significantly reduce the burden on Large Language Models (LLMs) Our results are the first in the literature to achieve state-of-the-art ranking performance on standard benchmarks using moderate-sized open-sourced LLMs.
  arXiv  Detail & Related papers  (2023-06-30T11:32:25Z)
• MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages [54.002969723086075]
  We evaluate cross-lingual open-retrieval question answering systems in 16 typologically diverse languages. The best system leveraging iteratively mined diverse negative examples achieves 32.2 F1, outperforming our baseline by 4.5 points. The second best system uses entity-aware contextualized representations for document retrieval, and achieves significant improvements in Tamil (20.8 F1), whereas most of the other systems yield nearly zero scores.
  arXiv  Detail & Related papers  (2022-07-02T06:54:10Z)
• CO-Search: COVID-19 Information Retrieval with Semantic Search, Question Answering, and Abstractive Summarization [53.67205506042232]
  CO-Search is a retriever-ranker semantic search engine designed to handle complex queries over the COVID-19 literature. To account for the domain-specific and relatively limited dataset, we generate a bipartite graph of document paragraphs and citations. We evaluate our system on the data of the TREC-COVID information retrieval challenge.
  arXiv  Detail & Related papers  (2020-06-17T01:32:48Z)

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.