Related papers: MERIT: Multilingual Semantic Retrieval with Interl…

Multilingual retrieval-augmented generation (mRAG) is often implemented within a fixed retrieval space, typically via query or document translation or multilingual embedding vector representations. However, this approach may be inadequate…

End-to-end text-image machine translation (TIMT), which directly translates textual content in images across languages, is crucial for real-world multilingual scene understanding. Despite advances in vision-language large models (VLLMs),…

Neural machine translation (NMT) from Chinese to low-resource Southeast Asian languages remains severely constrained by the extreme scarcity of clean parallel corpora and the pervasive noise in existing mined data. This chronic shortage not…

While pre-trained language models achieve impressive performance on various NLP benchmarks, they still struggle with tasks that require numerical reasoning. Recent advances in improving numerical reasoning are mostly achieved using very…

The integration of Retrieval-Augmented Generation (RAG) with Multimodal Large Language Models (MLLMs) has revolutionized information retrieval and expanded the practical applications of AI. However, current systems struggle in accurately…

With enhanced capabilities and widespread applications, Multimodal Large Language Models (MLLMs) are increasingly required to process and reason over multiple images simultaneously. However, existing MLLM benchmarks focus either on…

In Retrieval-Augmented Generation (RAG) tasks using Large Language Models (LLMs), the quality of retrieved information is critical to the final output. This paper introduces the IRSC benchmark for evaluating the performance of embedding…

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge to generate a response within a context with improved accuracy and reduced hallucinations. However, multi-modal RAG systems face…

Retrieval-Augmented Generation (RAG) has become a powerful paradigm for enhancing large language models (LLMs) through external knowledge retrieval. Despite its widespread attention, existing academic research predominantly focuses on…

Cross-modal retrieval (CMR) is a fundamental task in multimedia research, focused on retrieving semantically relevant targets across different modalities. While traditional CMR methods match text and image via embedding-based similarity…

The vocabulary gap is a core challenge in information retrieval (IR). In e-commerce applications like product search, the vocabulary gap is reported to be a bigger challenge than in more traditional application areas in IR, such as news…

Recent advancements in Retrieval-Augmented Language Models (RALMs) have demonstrated their efficacy in knowledge-intensive tasks. However, existing evaluation benchmarks often assume a single optimal approach to leveraging retrieved…

Advances in Natural Language Processing (NLP) have revolutionized the way researchers and practitioners address crucial societal problems. Large language models are now the standard to develop state-of-the-art solutions for text detection…

Existing Multimodal Large Language Models (MLLMs) are predominantly trained and tested on consistent visual-textual inputs, leaving open the question of whether they can handle inconsistencies in real-world, layout-rich content. To bridge…

Recently, integrating external tools with Large Language Models (LLMs) has gained significant attention as an effective strategy to mitigate the limitations inherent in their pre-training data. However, real-world systems often incorporate…

While large language models (LLMs) have achieved state-of-the-art performance on a wide range of medical question answering (QA) tasks, they still face challenges with hallucinations and outdated knowledge. Retrieval-augmented generation…

Multimodal document retrieval systems have shown strong progress in aligning visual and textual content for semantic search. However, most existing approaches remain heavily English-centric, limiting their effectiveness in multilingual…

Evaluating Information Retrieval (IR) systems relies on high-quality manual relevance judgments (qrels), which are costly and time-consuming to obtain. While pooling reduces the annotation effort, it results in only partially labeled…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in mainstream visual understanding tasks, but their ability to process action scenes that contradict everyday common sense remains undertested. To address…

The progress of composed image retrieval (CIR), a popular research direction in image retrieval, where a combined visual and textual query is used, is held back by the absence of high-quality training and evaluation data. We introduce a new…