Related papers: Hyperlink-induced Pre-training for Passage Retriev…

Self-Supervised Learning (SSL) methods typically rely on random image augmentations, or views, to make models invariant to different transformations. We hypothesize that the efficacy of pretraining pipelines based on conventional random…

Hallucinations in large language models (LLMs) present a growing challenge across real-world applications, from healthcare to law, where factual reliability is essential. Despite advances in alignment and instruction tuning, LLMs can still…

The objective in this paper is to improve the performance of text-to-image retrieval. To this end, we introduce a new framework that can boost the performance of large-scale pre-trained vision-language models, so that they can be used for…

Most existing large language models (LLMs) are expensive to adapt after deployment, especially when a task requires newly produced information or niche domain knowledge. Recent work has shown that, by manipulating and optimizing their…

The work of neural retrieval so far focuses on ranking short texts and is challenged with long documents. There are many cases where the users want to find a relevant passage within a long document from a huge corpus, e.g. Wikipedia…

Many discriminative natural language understanding (NLU) tasks have large label spaces. Learning such a process of large-space decision making is particularly challenging due to the lack of training instances per label and the difficulty of…

Whereas the recent emergence of large language models (LLMs) like ChatGPT has exhibited impressive general performance, it still has a large gap with fully-supervised models on specific tasks such as multi-span question answering. Previous…

How can we extend a pre-trained model to many language understanding tasks, without labeled or additional unlabeled data? Pre-trained language models (PLMs) have been effective for a wide range of NLP tasks. However, existing approaches…

Open-world object detection, as a more general and challenging goal, aims to recognize and localize objects described by arbitrary category names. The recent work GLIP formulates this problem as a grounding problem by concatenating all…

Large-scale but noisy image-text pair data have paved the way for the success of Contrastive Language-Image Pretraining (CLIP). As the foundation vision encoder, CLIP in turn serves as the cornerstone for most large vision-language models…

Objective: To automatically create large labeled training datasets and reduce the efforts of feature engineering for training accurate machine learning models for clinical information extraction. Materials and Methods: We propose a distant…

Dense retrieval has become a prominent method to obtain relevant context or world knowledge in open-domain NLP tasks. When we use a learned dense retriever on a retrieval corpus at inference time, an often-overlooked design choice is the…

Automatic Question Answering (QA) systems rely on contextual information to provide accurate answers. Commonly, contexts are prepared through either retrieval-based or generation-based methods. The former involves retrieving relevant…

Pre-trained Vision-Language Models (VLMs) such as CLIP have shown excellent generalization abilities. However, adapting these large-scale models to downstream tasks while preserving their generalization capabilities remains challenging.…

Text classification is one of the most imperative tasks in natural language processing (NLP). Recent advances with pre-trained language models (PLMs) have shown remarkable success on this task. However, the satisfying results obtained by…

Diffusion Language Models (DLMs) offer attractive advantages over Auto-Regressive (AR) models, such as full-attention parallel decoding and flexible generation. However, standard DLM training uses a static, single-step masked prediction…

Continual learning aims to enable a single model to learn a sequence of tasks without catastrophic forgetting. Top-performing methods usually require a rehearsal buffer to store past pristine examples for experience replay, which, however,…

Modern approaches to enhancing Large Language Models' factual accuracy and knowledge utilization face a fundamental trade-off: non-parametric retrieval-augmented generation (RAG) provides flexible access to external knowledge but suffers…

Multilingual representations pre-trained with monolingual data exhibit considerably unequal task performances across languages. Previous studies address this challenge with resource-intensive contextualized alignment, which assumes the…

Handling and digesting a huge amount of information in an efficient manner has been a long-term demand in modern society. Some solutions to map key points (short textual summaries capturing essential information and filtering redundancies)…