Vision-language Models (VLMs), such as CLIP and SigLIP, have become the de facto standard for multimodal tasks, serving as essential building blocks for recent Multimodal Large Language Models, including LLaVA and PaliGemma. However, current evaluations for VLMs remain heavily anchored to ImageNet. In this paper, we question whether ImageNet’s coverage is still sufficiently challenging for modern VLMs, and investigate the impact of adding novel and varied concept categories, i.e., semantically grouped fine-grained synsets. To this end, we introduce Concept-pedia, a novel, large-scale, semantically-annotated multimodal resource covering more than 165,000 concepts. Leveraging a language-agnostic, automatic annotation pipeline grounded in Wikipedia, Concept-pedia expands the range of visual concepts, including diverse abstract categories. Building on Concept-pedia, we also present a manually-curated Visual Concept Recognition evaluation benchmark, Concept-10k, that spans thousands of concepts across a wide range of categories. Our experiments show that current models, although excelling on ImageNet, struggle with Concept-10k. Not only do these findings highlight a persistent bias toward ImageNet-centric concepts, but they also underscore the urgent need for more representative benchmarks. By offering a broader and semantically richer testbed, Concept-10k aims to support the development of multimodal systems that better generalize to the complexities of real-world visual concepts.

Entity Linking and Entity Disambiguation systems aim to link entity mentions to their corresponding entries, typically represented by descriptions within a predefined, static knowledge base. Current models assume that these knowledge bases are complete and up-to-date, rendering them incapable of handling entities not yet included therein. However, in an ever-evolving world, new entities emerge regularly, making these static resources insufficient for practical applications. To address this limitation, we introduce RAED, a model that retrieves external knowledge to improve factual grounding in entity descriptions. Using sources such as Wikipedia, RAED effectively disambiguates entities and bases their descriptions on factual information, reducing the dependence on parametric knowledge. Our experiments show that retrieval not only enhances overall description quality metrics, but also reduces hallucinations. Moreover, despite not relying on fixed entity inventories, RAED outperforms systems that require predefined candidate sets at inference time on Entity Disambiguation. Finally, we show that descriptions generated by RAED provide useful entity representations for downstream Entity Linking models, leading to improved performance in the extremely challenging Emerging Entity Linking task.

Data scarcity is a prevalent challenge in the era of Large Language Models (LLMs). The insatiable hunger of LLMs for large corpora becomes even more pronounced when dealing with non-English and low-resource languages. The issue is particularly exacerbated in Semantic Parsing (SP), i.e. the task of converting text into a formal representation. The complexity of semantic formalisms makes training human annotators and subsequent data annotation unfeasible on a large scale, especially across languages. To mitigate this, we first introduce the Multilingual Semantic Layer (MSL), a conceptual evolution of previous formalisms, which decouples from disambiguation and external inventories and simplifies the task. MSL provides the necessary tools to encode the meaning across languages, paving the way for developing a high-quality semantic parsing dataset across different languages in a semi-automatic strategy. Subsequently, we manually refine a portion of this dataset and fine-tune GPT-3.5 to propagate these refinements across the dataset. Then, we manually annotate 1,100 sentences in eleven languages, including low-resource ones. Finally, we assess our dataset’s quality, showcasing the performance gap reduction across languages in Semantic Parsing.

Recent advancements in text summarization, particularly with the advent of Large Language Models (LLMs), have shown remarkable performance. However, a notable challenge persists as a substantial number of automatically-generated summaries exhibit factual inconsistencies, such as hallucinations. In response to this issue, various approaches for the evaluation of consistency for summarization have emerged. Yet, these newly-introduced metrics face several limitations, including lack of interpretability, focus on short document summaries (e.g., news articles), and computational impracticality, especially for LLM-based metrics. To address these shortcomings, we propose Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction (FENICE), a more interpretable and efficient factuality-oriented metric. FENICE leverages an NLI-based alignment between information in the source document and a set of atomic facts, referred to as claims, extracted from the summary. Our metric sets a new state of the art on AGGREFACT, the de-facto benchmark for factuality evaluation. Moreover, we extend our evaluation to a more challenging setting by conducting a human annotation process of long-form summarization. In the hope of fostering research in summarization factuality evaluation, we release the code of our metric and our factuality annotations of long-form summarization at https://github.com/Babelscape/FENICE.