Tootfinder

NOWJ@COLIEE 2025: A Multi-stage Framework Integrating Embedding Models and Large Language Models for Legal Retrieval and Entailment
Hoang-Trung Nguyen, Tan-Minh Nguyen, Xuan-Bach Le, Tuan-Kiet Le, Khanh-Huyen Nguyen, Ha-Thanh Nguyen, Thi-Hai-Yen Vuong, Le-Minh Nguyen
https://arxiv.org/abs/2509.08025

NOWJ@COLIEE 2025: A Multi-stage Framework Integrating Embedding Models and Large Language Models for Legal Retrieval and Entailment
This paper presents the methodologies and results of the NOWJ team's participation across all five tasks at the COLIEE 2025 competition, emphasizing advancements in the Legal Case Entailment task (Task 2). Our comprehensive approach systematically integrates pre-ranking models (BM25, BERT, monoT5), embedding-based semantic representations (BGE-m3, LLM2Vec), and advanced Large Language Models (Qwen-2, QwQ-32B, DeepSeek-V3) for summarization, relevance scoring, and contextual re-ranking. Specific…

A Re-ranking Method using K-nearest Weighted Fusion for Person Re-identification
Quang-Huy Che, Le-Chuong Nguyen, Gia-Nghia Tran, Dinh-Duy Phan, Vinh-Tiep Nguyen
https://arxiv.org/abs/2509.04050

A Re-ranking Method using K-nearest Weighted Fusion for Person Re-identification
In person re-identification, re-ranking is a crucial step to enhance the overall accuracy by refining the initial ranking of retrieved results. Previous studies have mainly focused on features from single-view images, which can cause view bias and issues like pose variation, viewpoint changes, and occlusions. Using multi-view features to present a person can help reduce view bias. In this work, we present an efficient re-ranking method that generates multi-view features by aggregating neighbors…

Reproducing and Extending Causal Insights Into Term Frequency Computation in Neural Rankers
Cile van Marken, Roxana Petcu
https://arxiv.org/abs/2510.06728 https://

Reproducing and Extending Causal Insights Into Term Frequency Computation in Neural Rankers
Neural ranking models have shown outstanding performance across a variety of tasks, such as document retrieval, re-ranking, question answering and conversational retrieval. However, the inner decision process of these models remains largely unclear, especially as models increase in size. Most interpretability approaches, such as probing, focus on correlational insights rather than establishing causal relationships. The paper 'Axiomatic Causal Interventions for Reverse Engineering Relevance Comp…

LLaVA-RE: Binary Image-Text Relevancy Evaluation with Multimodal Large Language Model
Tao Sun, Oliver Liu, JinJin Li, Lan Ma
https://arxiv.org/abs/2508.05602 https://

LLaVA-RE: Binary Image-Text Relevancy Evaluation with Multimodal Large Language Model
Multimodal generative AI usually involves generating image or text responses given inputs in another modality. The evaluation of image-text relevancy is essential for measuring response quality or ranking candidate responses. In particular, binary relevancy evaluation, i.e., ``Relevant'' vs. ``Not Relevant'', is a fundamental problem. However, this is a challenging task considering that texts have diverse formats and the definition of relevancy varies in different scenarios. We find that Multim…

ModernBERT ColBERT: Enhancing biomedical RAG through an advanced re-ranking retriever
Eduardo Mart\'inez Rivera, Filippo Menolascina
https://arxiv.org/abs/2510.04757 https…

ModernBERT + ColBERT: Enhancing biomedical RAG through an advanced re-ranking retriever
Retrieval-Augmented Generation (RAG) is a powerful technique for enriching Large Language Models (LLMs) with external knowledge, allowing for factually grounded responses, a critical requirement in high-stakes domains such as healthcare. However, the efficacy of RAG systems is fundamentally restricted by the performance of their retrieval module, since irrelevant or semantically misaligned documents directly compromise the accuracy of the final generated response. General-purpose dense retrieve…

Contrastive Retrieval Heads Improve Attention-Based Re-Ranking
Linh Tran, Yulong Li, Radu Florian, Wei Sun
https://arxiv.org/abs/2510.02219 https://arxiv.o…

Contrastive Retrieval Heads Improve Attention-Based Re-Ranking
The strong zero-shot and long-context capabilities of recent Large Language Models (LLMs) have paved the way for highly effective re-ranking systems. Attention-based re-rankers leverage attention weights from transformer heads to produce relevance scores, but not all heads are created equally: many contribute noise and redundancy, thus limiting performance. To address this, we introduce CoRe heads, a small set of retrieval heads identified via a contrastive scoring metric that explicitly reward…

Global-to-Local or Local-to-Global? Enhancing Image Retrieval with Efficient Local Search and Effective Global Re-ranking
Dror Aiger, Bingyi Cao, Kaifeng Chen, Andre Araujo
https://arxiv.org/abs/2509.04351

Global-to-Local or Local-to-Global? Enhancing Image Retrieval with Efficient Local Search and Effective Global Re-ranking
The dominant paradigm in image retrieval systems today is to search large databases using global image features, and re-rank those initial results with local image feature matching techniques. This design, dubbed global-to-local, stems from the computational cost of local matching approaches, which can only be afforded for a small number of retrieved images. However, emerging efficient local feature search approaches have opened up new possibilities, in particular enabling detailed retrieval at…

Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Search
Mengzhao Wang, Boyu Tan, Yunjun Gao, Hai Jin, Yingfeng Zhang, Xiangyu Ke, Xiaoliang Xu, Yifan Zhu
https://arxiv.org/abs/2508.01405

Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Search
Hybrid search, the integration of lexical and semantic retrieval, has become a cornerstone of modern information retrieval systems, driven by demanding applications like Retrieval-Augmented Generation (RAG). The architectural design space for these systems is vast and complex, yet a systematic, empirical understanding of the trade-offs among their core components--retrieval paradigms, combination schemes, and re-ranking methods--is critically lacking. To address this, and informed by our experi…

REALM: Recursive Relevance Modeling for LLM-based Document Re-Ranking
Pinhuan Wang, Zhiqiu Xia, Chunhua Liao, Feiyi Wang, Hang Liu
https://arxiv.org/abs/2508.18379 https://

REALM: Recursive Relevance Modeling for LLM-based Document Re-Ranking
Large Language Models (LLMs) have shown strong capabilities in document re-ranking, a key component in modern Information Retrieval (IR) systems. However, existing LLM-based approaches face notable limitations, including ranking uncertainty, unstable top-k recovery, and high token cost due to token-intensive prompting. To effectively address these limitations, we propose REALM, an uncertainty-aware re-ranking framework that models LLM-derived relevance as Gaussian distributions and refines them…

Bridging Language Gaps: Advances in Cross-Lingual Information Retrieval with Multilingual LLMs
Roksana Goworek, Olivia Macmillan-Scott, Eda B. \"Ozyi\u{g}it
https://arxiv.org/abs/2510.00908

Bridging Language Gaps: Advances in Cross-Lingual Information Retrieval with Multilingual LLMs
Cross-lingual information retrieval (CLIR) addresses the challenge of retrieving relevant documents written in languages different from that of the original query. Research in this area has typically framed the task as monolingual retrieval augmented by translation, treating retrieval methods and cross-lingual capabilities in isolation. Both monolingual and cross-lingual retrieval usually follow a pipeline of query expansion, ranking, re-ranking and, increasingly, question answering. Recent adv…

AIRwaves at CheckThat! 2025: Retrieving Scientific Sources for Implicit Claims on Social Media with Dual Encoders and Neural Re-Ranking
Cem Ashbaugh, Leon Baumg\"artner, Tim Gress, Nikita Sidorov, Daniel Werner
https://arxiv.org/abs/2509.19509

AIRwaves at CheckThat! 2025: Retrieving Scientific Sources for Implicit Claims on Social Media with Dual Encoders and Neural Re-Ranking
Linking implicit scientific claims made on social media to their original publications is crucial for evidence-based fact-checking and scholarly discourse, yet it is hindered by lexical sparsity, very short queries, and domain-specific language. Team AIRwaves ranked second in Subtask 4b of the CLEF-2025 CheckThat! Lab with an evidence-retrieval approach that markedly outperforms the competition baseline. The optimized sparse-retrieval baseline(BM25) achieves MRR@5 = 0.5025 on the gold label bli…

A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges
Rahul Raja, Anshaj Vats, Arpita Vats, Anirban Majumder
https://arxiv.org/abs/2507.21117

A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges
Recommender systems have traditionally followed modular architectures comprising candidate generation, multi-stage ranking, and re-ranking, each trained separately with supervised objectives and hand-engineered features. While effective in many domains, such systems face persistent challenges including sparse and noisy interaction data, cold-start problems, limited personalization depth, and inadequate semantic understanding of user and item content. The recent emergence of Large Language Model…

Optimizing Legal Document Retrieval in Vietnamese with Semi-Hard Negative Mining
Van-Hoang Le, Duc-Vu Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen
https://arxiv.org/abs/2507.14619

Optimizing Legal Document Retrieval in Vietnamese with Semi-Hard Negative Mining
Large Language Models (LLMs) face significant challenges in specialized domains like law, where precision and domain-specific knowledge are critical. This paper presents a streamlined two-stage framework consisting of Retrieval and Re-ranking to enhance legal document retrieval efficiency and accuracy. Our approach employs a fine-tuned Bi-Encoder for rapid candidate retrieval, followed by a Cross-Encoder for precise re-ranking, both optimized through strategic negative example mining. Key innov…

A Case Study of Balanced Query Recommendation on Wikipedia
Harshit Mishra, Sucheta Soundarajan
https://arxiv.org/abs/2508.20399 https://arxiv.org/pdf/2508.…

A Case Study of Balanced Query Recommendation on Wikipedia
Modern IR systems are an extremely important tool for seeking information. In addition to search, such systems include a number of query reformulation methods, such as query expansion and query recommendations, to provide high quality results. However, results returned by such methods sometimes exhibit undesirable or wrongful bias with respect to protected categories such as gender or race. Our earlier work considered the problem of balanced query recommendation, where instead of re-ranking a l…

D-RDW: Diversity-Driven Random Walks for News Recommender Systems
Runze Li, Lucien Heitz, Oana Inel, Abraham Bernstein
https://arxiv.org/abs/2508.13035 https://

D-RDW: Diversity-Driven Random Walks for News Recommender Systems
This paper introduces Diversity-Driven RandomWalks (D-RDW), a lightweight algorithm and re-ranking technique that generates diverse news recommendations. D-RDW is a societal recommender, which combines the diversification capabilities of the traditional random walk algorithms with customizable target distributions of news article properties. In doing so, our model provides a transparent approach for editors to incorporate norms and values into the recommendation process. D-RDW shows enhanced pe…