Sequran: Composite Scoring and Reranking Techniques for Refining Quran Search Engine Results

Query Generation with Direct Preference Optimization for Document Expansion in E-commerce Search

Doc2Query, a popular document expansion technique, leverages sequence-to-sequence models to generate relevant queries, effectively addressing the"vocabulary mismatch"problem in information retrieval. However, these models often suffer from generating either hallucinations unrelated to the document or repetitive content...

Retriever-Aware Query Rewriting for Tip-Of-The-Tongue Search via Preference Optimization

The strong independent performance of the Harrier-OSS model validates the use of decoder-only architectures for dense ToT retrieval, though the inclusion of simpler models like BM25 proved invaluable for enriching the rewrite training data, outperforming the query-rewrite focused runs published on TREC 2025.

Leveraging Language Models for Textual Retrieval in the TREC 2025 DRAGUN Track

Optimizing Multilingual Embedding Models for Retrieval and Reranking in RAG Pipelines: Enhancing Semantic Search in Turkish Medical Datasets

The findings indicate that domain-specialized models improve in-domain retrieval relative to generic models, and that systematic optimization through the multi-stage pipeline yields measurable gains in retrieval precision.

One-Step Retrieval Framework for Real-Time Sponsored Search Ads Using Hierarchical Text Representations

ANGLE integrates retrieval, relevance, and ranking directly within a single LLM, enabling precise and efficient ranking of ads by leveraging the full capabilities of the LLM.

Page-Aware Retrieval-Augmented Generation for EvalLLM 2026: A Five-Variant Study on French PDFs

Correct page selection, rather than semantic retrieval in isolation, is identified as the main opportunity for improvement in this setting of retrieval-augmented generation, with higher latency and more detected output artifacts.