Cross-modal entity linking refers to the ability to align entities and their attributes across different modalities. While cross-modal entity linking is a fundamental skill needed for real-world applications such as multimodal code generation, fake news detection, or scene understanding, it has not been thoroughly studied in the literature. In this paper, we introduce a new task and benchmark to address this gap. Our benchmark, MATE, consists of 5.5k evaluation instances featuring visual scenes aligned with their textual representations. To evaluate cross-modal entity linking performance, we design a question-answering task that involves retrieving one attribute of an object in one modality based on a unique attribute of that object in another modality. We evaluate state-of-the-art Vision-Language Models (VLMs) and humans on this task, and find that VLMs struggle significantly compared to humans, particularly as the number of objects in the scene increases. Our analysis also shows that, while chain-of-thought prompting can improve VLM performance, models remain far from achieving human-level proficiency. These findings highlight the need for further research in cross-modal entity linking and show that MATE is a strong benchmark to support that progress.

Existing Vision-Language Compositionality (VLC) benchmarks like SugarCrepe are formulated as image-to-text retrieval problems, where, given an image, the models need to select between the correct textual description and a synthetic hard negative text. In this work we present the Bidirectional Vision-Language Compositionality (BiVLC) dataset. The novelty of BiVLC is to add a synthetic hard negative image generated from the synthetic text, resulting in two image-to-text retrieval examples (one for each image) and, more importantly, two text-to-image retrieval examples (one for each text). Human annotators filter out ill-formed examples ensuring the validity of the benchmark. The experiments on BiVLC uncover a weakness of current multimodal models, as they perform poorly in the text-to-image direction. In fact, when considering both retrieval directions, the conclusions obtained in previous works change significantly. In addition to the benchmark, we show that a contrastive model trained using synthetic images and texts improves the state of the art in SugarCrepe and in BiVLC for both retrieval directions. The gap to human performance in BiVLC confirms that Vision-Language Compositionality is still a challenging problem. BiVLC and code are available at https://imirandam.github.io/BiVLC_project_page.

Large Language Models (LLMs) exhibit extensive knowledge about the world, but most evaluations have been limited to global or anglocentric subjects. This raises the question of how well these models perform on topics relevant to other cultures, whose presence on the web is not that prominent. To address this gap, we introduce BertaQA, a multiple-choice trivia dataset that is parallel in English and Basque. The dataset consists of a local subset with questions pertinent to the Basque culture, and a global subset with questions of broader interest. We find that state-of-the-art LLMs struggle with local cultural knowledge, even as they excel on global topics. However, we show that continued pre-training in Basque significantly improves the models' performance on Basque culture, even when queried in English. To our knowledge, this is the first solid evidence of knowledge transfer from a low-resource to a high-resource language. Our analysis sheds light on the complex interplay between language and knowledge, and reveals that some prior findings do not fully hold when reassessed on local topics. Our dataset and evaluation code are available under open licenses at https://github.com/juletx/BertaQA.

In this paper, we demonstrate how Large Language Models (LLMs) can effectively learn to use an off-the-shelf information retrieval (IR) system specifically when additional context is required to answer a given question. Given the performance of IR systems, the optimal strategy for question answering does not always entail external information retrieval; rather, it often involves leveraging the parametric memory of the LLM itself. Prior research has identified this phenomenon in the PopQA dataset, wherein the most popular questions are effectively addressed using the LLM's parametric memory, while less popular ones require IR system usage. Following this, we propose a tailored training approach for LLMs, leveraging existing open-domain question answering datasets. Here, LLMs are trained to generate a special token, , when they do not know the answer to a question. Our evaluation of the Adaptive Retrieval LLM (Adapt-LLM) on the PopQA dataset showcases improvements over the same LLM under three configurations: (i) retrieving information for all the questions, (ii) using always the parametric memory of the LLM, and (iii) using a popularity threshold to decide when to use a retriever. Through our analysis, we demonstrate that Adapt-LLM is able to generate the token when it determines that it does not know how to answer a question, indicating the need for IR, while it achieves notably high accuracy levels when it chooses to rely only on its parametric memory.

This paper shows that text-only Language Models (LM) can learn to ground spatial relations like "left of" or "below" if they are provided with explicit location information of objects and they are properly trained to leverage those locations. We perform experiments on a verbalized version of the Visual Spatial Reasoning (VSR) dataset, where images are coupled with textual statements which contain real or fake spatial relations between two objects of the image. We verbalize the images using an off-the-shelf object detector, adding location tokens to every object label to represent their bounding boxes in textual form. Given the small size of VSR, we do not observe any improvement when using locations, but pretraining the LM over a synthetic dataset automatically derived by us improves results significantly when using location tokens. We thus show that locations allow LMs to ground spatial relations, with our text-only LMs outperforming Vision-and-Language Models and setting the new state-of-the-art for the VSR dataset. Our analysis show that our text-only LMs can generalize beyond the relations seen in the synthetic dataset to some extent, learning also more useful information than that encoded in the spatial rules we used to create the synthetic dataset itself.

Existing work has observed that current text-to-image systems do not accurately reflect explicit spatial relations between objects such as 'left of' or 'below'. We hypothesize that this is because explicit spatial relations rarely appear in the image captions used to train these models. We propose an automatic method that, given existing images, generates synthetic captions that contain 14 explicit spatial relations. We introduce the Spatial Relation for Generation (SR4G) dataset, which contains 9.9 millions image-caption pairs for training, and more than 60 thousand captions for evaluation. In order to test generalization we also provide an 'unseen' split, where the set of objects in the train and test captions are disjoint. SR4G is the first dataset that can be used to spatially fine-tune text-to-image systems. We show that fine-tuning two different Stable Diffusion models (denoted as SD$_{SR4G}$) yields up to 9 points improvements in the VISOR metric. The improvement holds in the 'unseen' split, showing that SD$_{SR4G}$ is able to generalize to unseen objects. SD$_{SR4G}$ improves the state-of-the-art with fewer parameters, and avoids complex architectures. Our analysis shows that improvement is consistent for all relations. The dataset and the code will be publicly available.

Neural information retrieval requires costly annotated data for each target domain to be competitive. Synthetic annotation by query generation using Large Language Models or rulebased string manipulation has been proposed as an alternative, but their relative merits have not been analysed. In this paper, we compare both methods head-to-head using the same neural IR architecture. We focus on the BEIR benchmark, which includes test datasets from several domains with no training data, and explore two scenarios: zero-shot, where the supervised system is trained in a large out-ofdomain dataset (MS-MARCO); and unsupervised Figure 1: Experimental design: (left) a supervised retriever domain adaptation, where, in addition to is trained with manual annotations from MS-MS-MARCO, the system is fine-tuned in synthetic MARCO; (middle) an unsupervised retriever is trained data from the target domain. Our results with automatically generated queries for MS-MARCO indicate that Large Language Models outperform documents; (right) an unsupervised domain adaptation rule-based methods in all scenarios by a retriever is trained with both MS-MARCO manual annotations large margin, and, more importantly, that unsupervised and automatically generated queries in-domain domain adaptation is effective compared BEIR dataset documents. Evaluation is performed in to applying a supervised IR system in a BEIR producing two scenarios: zero-shot (left and middle zero-shot fashion. In addition we explore several retrievers); unsupervised domain adaptation (right sizes of open Large Language Models to retriever).

Translate-test is a popular technique to improve the performance of multilingual language models. This approach works by translating the input into English using an external machine translation system, and running inference over the translated input. However, these improvements can be attributed to the use of a separate translation system, which is typically trained on large amounts of parallel data not seen by the language model. In this work, we introduce a new approach called self-translate, which overcomes the need of an external translation system by leveraging the few-shot translation capabilities of multilingual language models. Experiments over 5 tasks show that self-translate consistently outperforms direct inference, demonstrating that language models are unable to leverage their full multilingual potential when prompted in non-English languages. Our code is available at https://github.com/juletx/self-translate.

Integrating outside knowledge for reasoning in visio-linguistic tasks such as visual question answering (VQA) is an open problem. Given that pretrained language models have been shown to include world knowledge, we propose to use a unimodal (text-only) train and inference procedure based on automatic off-the-shelf captioning of images and pretrained language models. Our results on a visual question answering task which requires external knowledge (OK-VQA) show that our text-only model outperforms pretrained multimodal (image-text) models of comparable number of parameters. In contrast, our model is less effective in a standard VQA task (VQA 2.0) confirming that our text-only method is specially effective for tasks requiring external knowledge. In addition, we show that our unimodal model is complementary to multimodal models in both OK-VQA and VQA 2.0, and yield the best result to date in OK-VQA among systems not using external knowledge graphs, and comparable to systems that do use them. Our qualitative analysis on OK-VQA reveals that automatic captions often fail to capture relevant information in the images, which seems to be balanced by the better inference ability of the text-only language models. Our work opens up possibilities to further improve inference in visio-linguistic tasks.

Generating an image from its textual description requires both a certain level of language understanding and common sense knowledge about the spatial relations of the physical entities being described. In this work, we focus on inferring the spatial relation between entities, a key step in the process of composing scenes based on text. More specifically, given a caption containing a mention to a subject and the location and size of the bounding box of that subject, our goal is to predict the location and size of an object mentioned in the caption. Previous work did not use the caption text information, but a manually provided relation holding between the subject and the object. In fact, the used evaluation datasets contain manually annotated ontological triplets but no captions, making the exercise unrealistic: a manual step was required; and systems did not leverage the richer information in captions. Here we present a system that uses the full caption, and Relations in Captions (REC-COCO), a dataset derived from MS-COCO which allows to evaluate spatial relation inference from captions directly. Our experiments show that: (1) it is possible to infer the size and location of an object with respect to a given subject directly from the caption; (2) the use of full text allows to place the object better than using a manually annotated relation. Our work paves the way for systems that, given a caption, decide which entities need to be depicted and their respective location and sizes, in order to then generate the final image.