MeVer at CheckThat! 2026: Cluster-Aware Hard-Negative Mining for Multilingual Scientific-Source Retrieval

• URL: http://arxiv.org/abs/2605.24236v1
• Date: Fri, 22 May 2026 21:24:14 GMT
• Title: MeVer at CheckThat! 2026: Cluster-Aware Hard-Negative Mining for Multilingual Scientific-Source Retrieval
• Abstract summary: We present our submission to CheckThat! 2026 Task 1 on multilingual scientific-source retrieval.<n>We propose cluster-aware hard-negative mining strategies that exploit the semantic structure of retrieved candidate pools.<n>Our experiments show that different hard-negative structures induce different retrieval behaviors.
• Score: 11.097006771680896
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Identifying the scientific source behind a social media claim requires matching short, informal, and often multilingual claims against large collections of scientific publications, where semantically related papers may act as challenging distractors or false negatives during training. We present our submission to CheckThat! 2026 Task 1 on multilingual scientific-source retrieval, focusing on how hard-negative mining should be adapted to multi-stage retrieval pipelines for scientific-source retrieval. We propose cluster-aware hard-negative mining strategies that exploit the semantic structure of retrieved candidate pools in order to construct more informative training negatives for dense retrieval and reranking. Our experiments show that different hard-negative structures induce different retrieval behaviors. Localized cluster negatives tend to favor precision-oriented retrieval, whereas broader non-gold semantic negatives provide stronger candidate coverage and more consistent reranking performance across languages. We further study multiple LLM-based evidence-selection formulations, including direct classification, pairwise comparison, and listwise reranking prompts, and find that constrained classification prompts provide the most reliable final document selection. The final system combines a dense retriever, a multilingual cross-encoder reranker, and a selective LLM-based disagreement resolver, ranking 6th among 37 submissions in the shared task evaluation. Overall, our results suggest that hard-negative mining should be treated as a stage-aware design problem rather than as a single retrieval optimization strategy.

Related papers

• Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval [17.695551248974215]
  UniME-R1 is an embedder-adviser framework that learns to reason over initially retrieved candidates.<n>UniME-R1 consistently improves retrieval performance over strong baselines.
  arXiv  Detail & Related papers  (2026-08-06T14:04:56Z)
• Disentangled Contrastive Learning for Zero-Shot Multilingual Dense Retrieval [18.12664959335536]
  We propose a disentangled contrastive learning(DCL) method for multilingual dense retrieval.<n>Specifically, we design disentangled optimization objectives based on hierarchical semantic alignment and language debiasing contrastive learning.<n>Our method consistently outperforms several strong baselines, demonstrating its effectiveness and generalization ability.
  arXiv  Detail & Related papers  (2026-08-03T13:13:15Z)
• Claim2Source at CheckThat! 2026: Improving Multilingual Scientific Claim-Source Retrieval with Verification-based Re-Ranking [17.04255262988263]
  We propose a multi-stage retrieval framework for multilingual scientific claim-source retrieval.<n>The framework employs bilingual claim representations, metadata-enhanced source representations, and language-specific adaptation of dense retrieval models.<n>Our approach achieves an average MRR@5 score of 0.7628 across English, German, and French claims, ranking first on the CheckThat! 2026 leaderboard.
  arXiv  Detail & Related papers  (2026-07-04T22:07:23Z)
• Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation [73.54930910609328]
  We propose LcRL, a multilingual search-augmented reinforcement learning framework.<n>LcRL integrates a language-coupled Group Relative Policy Optimization into the policy and reward models.<n>We adopt the language-coupled group sampling in the rollout module to reduce knowledge bias, and regularize an auxiliary anti-consistency penalty in the reward models to mitigate the knowledge conflict.
  arXiv  Detail & Related papers  (2026-01-21T11:32:32Z)
• The Overlooked Role of Graded Relevance Thresholds in Multilingual Dense Retrieval [7.238707143014165]
  We analyze how graded relevance scores and the threshold used to convert them into binary labels affect dense retrieval.<n>Using a multilingual dataset with LLM-annotated relevance scores, we examine monolingual, multilingual mixture, and cross-lingual retrieval scenarios.
  arXiv  Detail & Related papers  (2026-01-07T21:14:48Z)
• UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning [101.62386137855704]
  We present a novel Universal Multimodal Embedding (UniME-V2) model.<n>Our approach first constructs a potential hard negative set through global retrieval.<n>We then introduce the MLLM-as-a-Judge mechanism, which utilizes MLLMs to assess the semantic alignment of query-candidate pairs.<n>These scores serve as a foundation for hard negative mining, mitigating the impact of false negatives and enabling the identification of diverse, high-quality hard negatives.
  arXiv  Detail & Related papers  (2025-10-15T13:07:00Z)
• Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection [4.6738956348193]
  Large Language Models (LLMs) offer powerful capabilities for cross-lingual fact-checking.<n>LLMs often exhibit language bias, performing disproportionately better on high-resource languages such as English.<n>We present and inspect a novel concept - retrieval bias, when information retrieval systems tend to favor certain information over others.
  arXiv  Detail & Related papers  (2025-09-29T17:50:32Z)
• Boosting Data Utilization for Multilingual Dense Retrieval [47.16651389111977]
  We propose a method to boost data utilization for multilingual dense retrieval by obtaining high-quality hard negative samples and effective mini-batch data.<n>The experimental results on a multilingual retrieval benchmark, MIRACL, with 16 languages demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2025-09-11T13:42:50Z)
• Bridging the Training-Inference Gap for Dense Phrase Retrieval [104.4836127502683]
  Building dense retrievers requires a series of standard procedures, including training and validating neural models. In this paper, we explore how the gap between training and inference in dense retrieval can be reduced. We propose an efficient way of validating dense retrievers using a small subset of the entire corpus.
  arXiv  Detail & Related papers  (2022-10-25T00:53:06Z)
• Efficient Entity Candidate Generation for Low-Resource Languages [13.789451365205665]
  Candidate generation is a crucial module in entity linking. It plays a key role in multiple NLP tasks that have been proven to beneficially leverage knowledge bases. This paper constitutes an in-depth analysis of the candidate generation problem in the context of cross-lingual entity linking.
  arXiv  Detail & Related papers  (2022-06-30T09:49:53Z)
• IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages [87.5457337866383]
  We introduce the Image-Grounded Language Understanding Evaluation benchmark. IGLUE brings together visual question answering, cross-modal retrieval, grounded reasoning, and grounded entailment tasks across 20 diverse languages. We find that translate-test transfer is superior to zero-shot transfer and that few-shot learning is hard to harness for many tasks.
  arXiv  Detail & Related papers  (2022-01-27T18:53:22Z)
• On Cross-Lingual Retrieval with Multilingual Text Encoders [51.60862829942932]
  We study the suitability of state-of-the-art multilingual encoders for cross-lingual document and sentence retrieval tasks. We benchmark their performance in unsupervised ad-hoc sentence- and document-level CLIR experiments. We evaluate multilingual encoders fine-tuned in a supervised fashion (i.e., we learn to rank) on English relevance data in a series of zero-shot language and domain transfer CLIR experiments.
  arXiv  Detail & Related papers  (2021-12-21T08:10:27Z)

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.