Related papers: CLEAR: Cross-Lingual Enhancement in Alignment via …

Representation learning has significantly been developed with the advance of contrastive learning methods. Most of those methods have benefited from various data augmentations that are carefully designated to maintain their identities so…

Adapting large language models to other languages typically employs supervised fine-tuning (SFT) as a standard approach. However, it often suffers from an overemphasis on English performance, a phenomenon that is especially pronounced in…

There is extensive interest in metric learning methods for image retrieval. Many metric learning loss functions focus on learning a correct ranking of training samples, but strongly overfit semantically inconsistent labels and require a…

Contrastive learning has gained popularity and pushes state-of-the-art performance across numerous large-scale benchmarks. In contrastive learning, the contrastive loss function plays a pivotal role in discerning similarities between…

Reinforcement Learning (RL) algorithms often require long training to become useful, especially in complex environments with sparse rewards. While techniques like reward shaping and curriculum learning exist to accelerate training, these…

The cross-modal retrieval model leverages the potential of triple loss optimization to learn robust embedding spaces. However, existing methods often train these models in a singular pass, overlooking the distinction between semi-hard and…

The success of self-supervised contrastive learning hinges on identifying positive data pairs, such that when they are pushed together in embedding space, the space encodes useful information for subsequent downstream tasks. Constructing…

Retrieval systems generally focus on web-style queries that are short and underspecified. However, advances in language models have facilitated the nascent rise of retrieval models that can understand more complex queries with diverse…

In the field of language modeling, models augmented with retrieval components have emerged as a promising solution to address several challenges faced in the natural language processing (NLP) field, including knowledge grounding,…

In cross-lingual text classification, one seeks to exploit labeled data from one language to train a text classification model that can then be applied to a completely different language. Recent multilingual representation models have made…

In monolingual dense retrieval, lots of works focus on how to distill knowledge from cross-encoder re-ranker to dual-encoder retriever and these methods achieve better performance due to the effectiveness of cross-encoder re-ranker.…

We focus on the problem of search in the multilingual setting. Examining the problems of next-sentence prediction and inverse cloze, we show that at large scale, instance-based transfer learning is surprisingly effective in the multilingual…

Multilingual Large Language Models (LLMs) offer powerful capabilities for cross-lingual fact-checking. However, these models often exhibit language bias, performing disproportionately better on high-resource languages such as English than…

In this study, we investigate interaction-based neural matching models for ad-hoc cross-lingual information retrieval (CLIR) using cross-lingual word embeddings (CLWEs). With experiments conducted on the CLEF collection over four language…

Human perception of visual similarity is inherently adaptive and subjective, depending on the users' interests and focus. However, most image retrieval systems fail to reflect this flexibility, relying on a fixed, monolithic metric that…

Open-vocabulary audio language models (ALMs), like Contrastive Language Audio Pretraining (CLAP), represent a promising new paradigm for audio-text retrieval using natural language queries. In this paper, for the first time, we perform…

Large language models (LLMs) have demonstrated competitive performance in zero-shot multilingual machine translation (MT). Some follow-up works further improved MT performance via preference optimization, but they leave a key aspect largely…

The Contrastive Language-Audio Pretraining (CLAP) model has demonstrated excellent performance in general audio description-related tasks, such as audio retrieval. However, in the emerging field of emotional speaking style description…

Schema matching is a crucial task in data integration, involving the alignment of a source schema with a target schema to establish correspondence between their elements. This task is challenging due to textual and semantic heterogeneity,…

Cross-lingual retrieval-augmented generation (RAG) is a critical capability for retrieving and generating answers across languages. Prior work in this context has mostly focused on generation and relied on benchmarks derived from…