paper-with-me

Papers

Improving Document Retrieval Coherence for Semantically Equivalent Queries

2025-08-11 · Stefano Campese, Alessandro Moschitti, Ivano Lauriola arxiv

Dense Retrieval (DR) models have proven to be effective for Document Retrieval and Information Grounding tasks. Usually, these models are trained and optimized for improving the relevance of top-ranked documents for a given query. Previous work has shown that popular DR models are sensitive to the query and document lexicon: small variations of it may lead to a significant difference in the set of retrieved documents. In this paper, we propose a variation of the Multi-Negative Ranking loss for training DR that improves the coherence of models in retrieving the same documents with respect to semantically similar queries. The loss penalizes discrepancies between the top-k ranked documents retrieved for diverse but semantic equivalent queries. We conducted extensive experiments on various datasets, MS-MARCO, Natural Questions, BEIR, and TREC DL 19/20. The results show that (i) models optimizes by our loss are subject to lower sensitivity, and, (ii) interestingly, higher accuracy.

📄 PDF Abstract BibTeX arXiv:2508.07975

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Questions

Similar Papers 제목 키워드 기반

LAMAR: An Open Language-Aware Multilingual Alignment Reranker

2026-07-24 · Seongtae Hong, Youngjoon Jang, Jungseob Lee, Seungyoon Lee 외 hf

In multilingual retrieval augmented generation, a retriever can retrieve relevant documents written in multiple languages, which are subsequently reranked before answer generation. However, it remains unclear whether exi…

Answer Generation

MLDocRAG: Multimodal Long-Context Document Retrieval Augmented Generation

2026-02-10 · Yongyue Zhang, Yaxiong Wu arxiv

Understanding multimodal long-context documents that comprise multimodal chunks such as paragraphs, figures, and tables is challenging due to (1) cross-modal heterogeneity to localize relevant information across modaliti…

Long-Context UnderstandingQuestion Answering

Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark

2025-12-23 · Hao Guo, Xugong Qin, Jun Jie Ou Yang, Peng Zhang 외 arxiv

Document image retrieval (DIR) aims to retrieve document images from a gallery according to a given query. Existing DIR methods are primarily based on image queries that retrieve documents within the same coarse semantic…

Image Retrieval

Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark

2025-01-01 · CVPR 2025 1 · Hao Guo, Xugong Qin, Jun Jie Ou Yang, Peng Zhang 외

Document image retrieval (DIR) aims to retrieve document images from a gallery according to a given query. Existing DIR methods are primarily based on image queries that retrieve documents within the same coarse sema…

document understandingImage RetrievalOptical Character Recognition (OCR)Retrieval

Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrieval

2024-10-17 · Yu Xia, Junda Wu, Sungchul Kim, Tong Yu 외

Large language models (LLMs) have been used to generate query expansions augmenting original queries for improving information search. Recent studies also explore providing LLMs with initial retrieval results to generate…

Retrieval