Sandro Pezzelle

Michael Hanna, Yonatan Belinkov, Sandro Pezzelle

Animacy - whether an entity is alive and sentient - is fundamental to cognitive processing, impacting areas such as memory, vision, and language. However, animacy is not always expressed directly in language: in English it often manifests indirectly, in the form of selectional constraints on verbs and adjectives. This poses a potential issue for transformer language models (LMs): they often train only on text, and thus lack access to extralinguistic information from which humans learn about animacy. We ask: how does this impact LMs' animacy processing - do they still behave as humans do? We answer this question using open-source LMs. Like previous studies, we find that LMs behave much like humans when presented with entities whose animacy is typical. However, we also show that even when presented with stories about atypically animate entities, such as a peanut in love, LMs adapt: they treat these entities as animate, though they do not adapt as well as humans. Even when the context indicating atypical animacy is very short, LMs pick up on subtle clues and change their behavior. We conclude that despite the limited signal through which LMs can learn about animacy, they are indeed sensitive to the relevant lexical semantic nuances available in English.

Anna Bavaresco, Marianne de Heer Kloots, Sandro Pezzelle et al.

Recent studies suggest that transformer-based vision-language models (VLMs) capture the multimodality of concept processing in the human brain. However, a systematic evaluation exploring different types of VLM architectures and the role played by visual and textual context is still lacking. Here, we analyse multiple VLMs employing different strategies to integrate visual and textual modalities, along with language-only counterparts. We measure the alignment between concept representations by models and existing (fMRI) brain responses to concept words presented in two experimental conditions, where either visual (pictures) or textual (sentences) context is provided. Our results reveal that VLMs outperform the language-only counterparts in both experimental conditions. However, controlled ablation studies show that only for some VLMs, such as LXMERT and IDEFICS2, brain alignment stems from genuinely learning more human-like concepts during pretraining, while others are highly sensitive to the context provided at inference. Additionally, we find that vision-language encoders are more brain-aligned than more recent, generative VLMs. Altogether, our study shows that VLMs align with human neural representations in concept processing, while highlighting differences among architectures. We open-source code and materials to reproduce our experiments at: https://github.com/dmg-illc/vl-concept-processing.

Aditya K Surikuchi, Sandro Pezzelle, Raquel Fernández

A proper evaluation of stories generated for a sequence of images -- the task commonly referred to as visual storytelling -- must consider multiple aspects, such as coherence, grammatical correctness, and visual grounding. In this work, we focus on evaluating the degree of grounding, that is, the extent to which a story is about the entities shown in the images. We analyze current metrics, both designed for this purpose and for general vision-text alignment. Given their observed shortcomings, we propose a novel evaluation tool, GROOViST, that accounts for cross-modal dependencies, temporal misalignments (the fact that the order in which entities appear in the story and the image sequence may not match), and human intuitions on visual grounding. An additional advantage of GROOViST is its modular design, where the contribution of each component can be assessed and interpreted individually.

Xinyi Chen, Raquel Fernández, Sandro Pezzelle

Despite the impressive performance achieved by pre-trained language-and-vision models in downstream tasks, it remains an open question whether this reflects a proper understanding of image-text interaction. In this work, we explore to what extent they handle basic linguistic constructions -- active-passive voice, coordination, and relative clauses -- that even preschool children can typically master. We present BLA, a novel, automatically constructed benchmark to evaluate multimodal models on these Basic Language Abilities. We show that different types of Transformer-based systems, such as CLIP, ViLBERT, and BLIP2, generally struggle with BLA in a zero-shot setting, in line with previous findings. Our experiments, in particular, show that most of the tested models only marginally benefit when fine-tuned or prompted with construction-specific samples. Yet, the generative BLIP2 shows promising trends, especially in an in-context learning setting. This opens the door to using BLA not only as an evaluation benchmark but also to improve models' basic language abilities.

Aditya K Surikuchi, Raquel Fernández, Sandro Pezzelle

Visual storytelling consists in generating a natural language story given a temporally ordered sequence of images. This task is not only challenging for models, but also very difficult to evaluate with automatic metrics since there is no consensus about what makes a story 'good'. In this paper, we introduce a novel method that measures story quality in terms of human likeness regarding three key aspects highlighted in previous work: visual grounding, coherence, and repetitiveness. We then use this method to evaluate the stories generated by several models, showing that the foundation model LLaVA obtains the best result, but only slightly so compared to TAPM, a 50-times smaller visual storytelling model. Upgrading the visual and language components of TAPM results in a model that yields competitive performance with a relatively low number of parameters. Finally, we carry out a human evaluation study, whose results suggest that a 'good' story may require more than a human-like level of visual grounding, coherence, and repetition.

Giovanni Cinà, Daniel Fernandez-Llaneza, Ludovico Deponte et al.

Feature attribution methods have become a staple method to disentangle the complex behavior of black box models. Despite their success, some scholars have argued that such methods suffer from a serious flaw: they do not allow a reliable interpretation in terms of human concepts. Simply put, visualizing an array of feature contributions is not enough for humans to conclude something about a model's internal representations, and confirmation bias can trick users into false beliefs about model behavior. We argue that a structured approach is required to test whether our hypotheses on the model are confirmed by the feature attributions. This is what we call the "semantic match" between human concepts and (sub-symbolic) explanations. Building on the conceptual framework put forward in Cinà et al. [2023], we propose a structured approach to evaluate semantic match in practice. We showcase the procedure in a suite of experiments spanning tabular and image data, and show how the assessment of semantic match can give insight into both desirable (e.g., focusing on an object relevant for prediction) and undesirable model behaviors (e.g., focusing on a spurious correlation). We couple our experimental results with an analysis on the metrics to measure semantic match, and argue that this approach constitutes the first step towards resolving the issue of confirmation bias in XAI.

Sandro Pezzelle

Intelligent systems that aim at mastering language as humans do must deal with its semantic underspecification, namely, the possibility for a linguistic signal to convey only part of the information needed for communication to succeed. Consider the usages of the pronoun they, which can leave the gender and number of its referent(s) underspecified. Semantic underspecification is not a bug but a crucial language feature that boosts its storage and processing efficiency. Indeed, human speakers can quickly and effortlessly integrate semantically-underspecified linguistic signals with a wide range of non-linguistic information, e.g., the multimodal context, social or cultural conventions, and shared knowledge. Standard NLP models have, in principle, no or limited access to such extra information, while multimodal systems grounding language into other modalities, such as vision, are naturally equipped to account for this phenomenon. However, we show that they struggle with it, which could negatively affect their performance and lead to harmful consequences when used for applications. In this position paper, we argue that our community should be aware of semantic underspecification if it aims to develop language technology that can successfully interact with human users. We discuss some applications where mastering it is crucial and outline a few directions toward achieving this goal.

Lars Buijtelaar, Sandro Pezzelle

This work studies the semantic representations learned by BERT for compounds, that is, expressions such as sunlight or bodyguard. We build on recent studies that explore semantic information in Transformers at the word level and test whether BERT aligns with human semantic intuitions when dealing with expressions (e.g., sunlight) whose overall meaning depends -- to a various extent -- on the semantics of the constituent words (sun, light). We leverage a dataset that includes human judgments on two psycholinguistic measures of compound semantic analysis: lexeme meaning dominance (LMD; quantifying the weight of each constituent toward the compound meaning) and semantic transparency (ST; evaluating the extent to which the compound meaning is recoverable from the constituents' semantics). We show that BERT-based measures moderately align with human intuitions, especially when using contextualized representations, and that LMD is overall more predictable than ST. Contrary to the results reported for 'standard' words, higher, more contextualized layers are the best at representing compound meaning. These findings shed new light on the abilities of BERT in dealing with fine-grained semantic phenomena. Moreover, they can provide insights into how speakers represent compounds.

Yunchong Huang, Gianni Barlacchi, Sandro Pezzelle

Large language models (LLMs) perform well on well-posed questions, yet standard question-answering (QA) benchmarks remain far from solved. We argue that this gap is partly due to underspecified questions - queries whose interpretation cannot be uniquely determined without additional context. To test this hypothesis, we introduce an LLM-based classifier to identify underspecified questions and apply it to several widely used QA datasets, finding that 16% to over 50% of benchmark questions are underspecified and that LLMs perform significantly worse on them. To isolate the effect of underspecification, we conduct a controlled rewriting experiment that serves as an upper-bound analysis, rewriting underspecified questions into fully specified variants while holding gold answers fixed. QA performance consistently improves under this setting, indicating that many apparent QA failures stem from question underspecification rather than model limitations. Our findings highlight underspecification as an important confound in QA evaluation and motivate greater attention to question clarity in benchmark design.

Aditya K Surikuchi, Raquel Fernández, Sandro Pezzelle

Foundation models are used for many real-world applications involving language generation from temporally-ordered multimodal events. In this work, we study the ability of models to identify the most important sub-events in a video, which is a fundamental prerequisite for narrating or summarizing multimodal events. Specifically, we focus on football games and evaluate models on their ability to distinguish between important and non-important sub-events in a game. To this end, we construct a new dataset by leveraging human preferences for importance implicit in football game highlight reels, without any additional annotation costs. Using our dataset, we compare several state-of-the-art multimodal models and show that they are not far from chance level performance. Analyses of models beyond standard evaluation metrics reveal their tendency to rely on a single dominant modality and their ineffectiveness in synthesizing necessary information from multiple sources. Our findings underline the importance of modular architectures that can handle sample-level heterogeneity in multimodal data and the need for complementary training procedures that can maximize cross-modal synergy.

Zoë Prins, Samuele Punzo, Frank Wildenburg et al.

Standard evaluations of Large language models (LLMs) focus on task performance, offering limited insight into whether correct behavior reflects appropriate underlying mechanisms and risking confirmation bias. We introduce a simple, principled interpretability framework based on token-level perplexity to test whether models rely on linguistically relevant cues. By comparing perplexity distributions over minimal sentence pairs differing in one or a few `pivotal' tokens, our method enables precise, hypothesis-driven analysis without relying on unstable feature-attribution techniques. Experiments on controlled linguistic benchmarks with several open-weight LLMs show that, while linguistically important tokens influence model behavior, they never fully explain perplexity shifts, revealing that models rely on heuristics other than the expected linguistic ones.

Michael Hanna, Sandro Pezzelle, Yonatan Belinkov

Many recent language model (LM) interpretability studies have adopted the circuits framework, which aims to find the minimal computational subgraph, or circuit, that explains LM behavior on a given task. Most studies determine which edges belong in a LM's circuit by performing causal interventions on each edge independently, but this scales poorly with model size. Edge attribution patching (EAP), gradient-based approximation to interventions, has emerged as a scalable but imperfect solution to this problem. In this paper, we introduce a new method - EAP with integrated gradients (EAP-IG) - that aims to better maintain a core property of circuits: faithfulness. A circuit is faithful if all model edges outside the circuit can be ablated without changing the model's performance on the task; faithfulness is what justifies studying circuits, rather than the full model. Our experiments demonstrate that circuits found using EAP are less faithful than those found using EAP-IG, even though both have high node overlap with circuits found previously using causal interventions. We conclude more generally that when using circuits to compare the mechanisms models use to solve tasks, faithfulness, not overlap, is what should be measured.

Kumiko Nakajima, Jan Zuiderveld, Sandro Pezzelle

Large language models (LLMs) are increasingly used in verbal creative tasks. However, previous assessments of the creative capabilities of LLMs remain weakly grounded in human creativity theory and are thus hard to interpret. The widely used Divergent Association Task (DAT) focuses on novelty, ignoring appropriateness, a core component of creativity. We evaluate a range of state-of-the-art LLMs on DAT and show that their scores on the task are lower than those of two baselines that do not possess any creative abilities, undermining its validity for model evaluation. Grounded in human creativity theory, which defines creativity as the combination of novelty and appropriateness, we introduce Conditional Divergent Association Task (CDAT). CDAT evaluates novelty conditional on contextual appropriateness, separating noise from creativity better than DAT, while remaining simple and objective. Under CDAT, smaller model families often show the most creativity, whereas advanced families favor appropriateness at lower novelty. We hypothesize that training and alignment likely shift models along this frontier, making outputs more appropriate but less creative. We release the dataset and code.

Frank Wildenburg, Michael Hanna, Sandro Pezzelle

In everyday language use, speakers frequently utter and interpret sentences that are semantically underspecified, namely, whose content is insufficient to fully convey their message or interpret them univocally. For example, to interpret the underspecified sentence "Don't spend too much", which leaves implicit what (not) to spend, additional linguistic context or outside knowledge is needed. In this work, we propose a novel Dataset of semantically Underspecified Sentences grouped by Type (DUST) and use it to study whether pre-trained language models (LMs) correctly identify and interpret underspecified sentences. We find that newer LMs are reasonably able to identify underspecified sentences when explicitly prompted. However, interpreting them correctly is much harder for any LMs. Our experiments show that when interpreting underspecified sentences, LMs exhibit little uncertainty, contrary to what theoretical accounts of underspecification would predict. Overall, our study reveals limitations in current models' processing of sentence semantics and highlights the importance of using naturalistic data and communicative scenarios when evaluating LMs' language capabilities.

Alberto Testoni, Juell Sprott, Sandro Pezzelle

While human speakers use a variety of different expressions when describing the same object in an image, giving rise to a distribution of plausible labels driven by pragmatic constraints, the extent to which current Vision & Language Large Language Models (VLLMs) can mimic this crucial feature of language use is an open question. This applies to common, everyday objects, but it is particularly interesting for uncommon or novel objects for which a category label may be lacking or fuzzy. Furthermore, similar patterns of variation are observed among human speakers for highly context-sensitive expressions, such as the quantifiers 'few' or 'most'. In our work, we evaluate VLLMs (FROMAGe, BLIP-2, LLaVA) on three categories (nouns, attributes, and quantifiers) where humans show great subjective variability concerning the distribution over plausible labels, using datasets and resources mostly under-explored in previous work. Our results reveal mixed evidence on the ability of VLLMs to capture human naming preferences at generation time: while some models are good at mimicking human distributions for nouns and attributes, all of them fail to assign quantifiers, a task that requires more accurate, high-level reasoning.

Michael Hanna, Yonatan Belinkov, Sandro Pezzelle

Although large language models (LLMs) are increasingly capable, these capabilities are unevenly distributed: they excel at formal linguistic tasks, such as producing fluent, grammatical text, but struggle more with functional linguistic tasks like reasoning and consistent fact retrieval. Inspired by neuroscience, recent work suggests that to succeed on both formal and functional linguistic tasks, LLMs should use different mechanisms for each; such localization could either be built-in or emerge spontaneously through training. In this paper, we ask: do current models, with fast-improving functional linguistic abilities, exhibit distinct localization of formal and functional linguistic mechanisms? We answer this by finding and comparing the "circuits", or minimal computational subgraphs, responsible for various formal and functional tasks. Comparing 5 LLMs across 10 distinct tasks, we find that while there is indeed little overlap between circuits for formal and functional tasks, there is also little overlap between formal linguistic tasks, as exists in the human brain. Thus, a single formal linguistic network, unified and distinct from functional task circuits, remains elusive. However, in terms of cross-task faithfulness - the ability of one circuit to solve another's task - we observe a separation between formal and functional mechanisms, suggesting that shared mechanisms between formal tasks may exist.

Ece Takmaz, Sandro Pezzelle, Raquel Fernández

There is an intricate relation between the properties of an image and how humans behave while describing the image. This behavior shows ample variation, as manifested in human signals such as eye movements and when humans start to describe the image. Despite the value of such signals of visuo-linguistic variation, they are virtually disregarded in the training of current pretrained models, which motivates further investigation. Using a corpus of Dutch image descriptions with concurrently collected eye-tracking data, we explore the nature of the variation in visuo-linguistic signals, and find that they correlate with each other. Given this result, we hypothesize that variation stems partly from the properties of the images, and explore whether image representations encoded by pretrained vision encoders can capture such variation. Our results indicate that pretrained models do so to a weak-to-moderate degree, suggesting that the models lack biases about what makes a stimulus complex for humans and what leads to variations in human outputs.

Nathanaël Carraz Rakotonirina, Mohammed Hamdy, Jon Ander Campos et al.

Large Language Models (LLMs) are increasingly used in working environments for a wide range of tasks, excelling at solving individual problems in isolation. However, are they also able to effectively collaborate over long-term interactions? To investigate this, we introduce MemoryCode, a synthetic multi-session dataset designed to test LLMs' ability to track and execute simple coding instructions amid irrelevant information, simulating a realistic setting. While all the models we tested handle isolated instructions well, even the performance of state-of-the-art models like GPT-4o deteriorates when instructions are spread across sessions. Our analysis suggests this is due to their failure to retrieve and integrate information over long instruction chains. Our results highlight a fundamental limitation of current LLMs, restricting their ability to collaborate effectively in long interactions.

Leonardo Bertolazzi, Sandro Pezzelle, Raffaelle Bernardi

Both humans and large language models (LLMs) exhibit content effects: biases in which the plausibility of the semantic content of a reasoning problem influences judgments regarding its logical validity. While this phenomenon in humans is best explained by the dual-process theory of reasoning, the mechanisms behind content effects in LLMs remain unclear. In this work, we address this issue by investigating how LLMs encode the concepts of validity and plausibility within their internal representations. We show that both concepts are linearly represented and strongly aligned in representational geometry, leading models to conflate plausibility with validity. Using steering vectors, we demonstrate that plausibility vectors can causally bias validity judgements, and vice versa, and that the degree of alignment between these two concepts predicts the magnitude of behavioral content effects across models. Finally, we construct debiasing vectors that disentangle these concepts, reducing content effects and improving reasoning accuracy. Our findings advance understanding of how abstract logical concepts are represented in LLMs and highlight representational interventions as a path toward more logical systems.

Aditya K Surikuchi, Raquel Fernández, Sandro Pezzelle

In recent years, a substantial body of work in visually grounded natural language processing has focused on real-life multimodal scenarios such as describing content depicted in images or videos. However, comparatively less attention has been devoted to study the nature and degree of interaction between the different modalities in these scenarios. In this paper, we argue that any task dealing with natural language generation from sequences of images or frames is an instance of the broader, more general problem of modeling the intricate relationships between visual events unfolding over time and the features of the language used to interpret, describe, or narrate them. Therefore, solving these tasks requires models to be capable of identifying and managing such intricacies. We consider five seemingly different tasks, which we argue are compelling instances of this broader multimodal problem. Subsequently, we survey the modeling and evaluation approaches adopted for these tasks in recent years and examine the common set of challenges these tasks pose. Building on this perspective, we identify key open questions and propose several research directions for future investigation.

Anna Bavaresco, Raffaella Bernardi, Leonardo Bertolazzi et al.

There is an increasing trend towards evaluating NLP models with LLMs instead of human judgments, raising questions about the validity of these evaluations, as well as their reproducibility in the case of proprietary models. We provide JUDGE-BENCH, an extensible collection of 20 NLP datasets with human annotations covering a broad range of evaluated properties and types of data, and comprehensively evaluate 11 current LLMs, covering both open-weight and proprietary models, for their ability to replicate the annotations. Our evaluations show substantial variance across models and datasets. Models are reliable evaluators on some tasks, but overall display substantial variability depending on the property being evaluated, the expertise level of the human judges, and whether the language is human or model-generated. We conclude that LLMs should be carefully validated against human judgments before being used as evaluators.

Ece Takmaz, Nicolo' Brandizzi, Mario Giulianelli et al.

Dialogue participants may have varying levels of knowledge about the topic under discussion. In such cases, it is essential for speakers to adapt their utterances by taking their audience into account. Yet, it is an open question how such adaptation can be modelled in computational agents. In this paper, we model a visually grounded referential game between a knowledgeable speaker and a listener with more limited visual and linguistic experience. Inspired by psycholinguistic theories, we endow our speaker with the ability to adapt its referring expressions via a simulation module that monitors the effectiveness of planned utterances from the listener's perspective. We propose an adaptation mechanism building on plug-and-play approaches to controlled language generation, where utterance generation is steered on the fly by the simulator without finetuning the speaker's underlying language model. Our results and analyses show that our approach is effective: the speaker's utterances become closer to the listener's domain of expertise, which leads to higher communicative success.

Ece Takmaz, Sandro Pezzelle, Lisa Beinborn et al.

When speakers describe an image, they tend to look at objects before mentioning them. In this paper, we investigate such sequential cross-modal alignment by modelling the image description generation process computationally. We take as our starting point a state-of-the-art image captioning system and develop several model variants that exploit information from human gaze patterns recorded during language production. In particular, we propose the first approach to image description generation where visual processing is modelled $\textit{sequentially}$. Our experiments and analyses confirm that better descriptions can be obtained by exploiting gaze-driven attention and shed light on human cognitive processes by comparing different ways of aligning the gaze modality with language production. We find that processing gaze data sequentially leads to descriptions that are better aligned to those produced by speakers, more diverse, and more natural${-}$particularly when gaze is encoded with a dedicated recurrent component.

Ece Takmaz, Mario Giulianelli, Sandro Pezzelle et al.

Dialogue participants often refer to entities or situations repeatedly within a conversation, which contributes to its cohesiveness. Subsequent references exploit the common ground accumulated by the interlocutors and hence have several interesting properties, namely, they tend to be shorter and reuse expressions that were effective in previous mentions. In this paper, we tackle the generation of first and subsequent references in visually grounded dialogue. We propose a generation model that produces referring utterances grounded in both the visual and the conversational context. To assess the referring effectiveness of its output, we also implement a reference resolution system. Our experiments and analyses show that the model produces better, more effective referring utterances than a model not grounded in the dialogue context, and generates subsequent references that exhibit linguistic patterns akin to humans.

Sandro Pezzelle, Raquel Fernández

This work aims at modeling how the meaning of gradable adjectives of size (`big', `small') can be learned from visually-grounded contexts. Inspired by cognitive and linguistic evidence showing that the use of these expressions relies on setting a threshold that is dependent on a specific context, we investigate the ability of multi-modal models in assessing whether an object is `big' or `small' in a given visual scene. In contrast with the standard computational approach that simplistically treats gradable adjectives as `fixed' attributes, we pose the problem as relational: to be successful, a model has to consider the full visual context. By means of four main tasks, we show that state-of-the-art models (but not a relatively strong baseline) can learn the function subtending the meaning of size adjectives, though their performance is found to decrease while moving from simple to more complex tasks. Crucially, models fail in developing abstract representations of gradable adjectives that can be used compositionally.

Shailza Jolly, Sandro Pezzelle, Tassilo Klein et al.

We introduce MASSES, a simple evaluation metric for the task of Visual Question Answering (VQA). In its standard form, the VQA task is operationalized as follows: Given an image and an open-ended question in natural language, systems are required to provide a suitable answer. Currently, model performance is evaluated by means of a somehow simplistic metric: If the predicted answer is chosen by at least 3 human annotators out of 10, then it is 100% correct. Though intuitively valuable, this metric has some important limitations. First, it ignores whether the predicted answer is the one selected by the Majority (MA) of annotators. Second, it does not account for the quantitative Subjectivity (S) of the answers in the sample (and dataset). Third, information about the Semantic Similarity (SES) of the responses is completely neglected. Based on such limitations, we propose a multi-component metric that accounts for all these issues. We show that our metric is effective in providing a more fine-grained evaluation both on the quantitative and qualitative level.

Sandro Pezzelle, Shane Steinert-Threlkeld, Raffaela Bernardi et al.

We study the role of linguistic context in predicting quantifiers (`few', `all'). We collect crowdsourced data from human participants and test various models in a local (single-sentence) and a global context (multi-sentence) condition. Models significantly out-perform humans in the former setting and are only slightly better in the latter. While human performance improves with more linguistic context (especially on proportional quantifiers), model performance suffers. Models are very effective in exploiting lexical and morpho-syntactic patterns; humans are better at genuinely understanding the meaning of the (global) context.

Sandro Pezzelle, Ionut-Teodor Sorodoc, Raffaella Bernardi

The present work investigates whether different quantification mechanisms (set comparison, vague quantification, and proportional estimation) can be jointly learned from visual scenes by a multi-task computational model. The motivation is that, in humans, these processes underlie the same cognitive, non-symbolic ability, which allows an automatic estimation and comparison of set magnitudes. We show that when information about lower-complexity tasks is available, the higher-level proportional task becomes more accurate than when performed in isolation. Moreover, the multi-task model is able to generalize to unseen combinations of target/non-target objects. Consistently with behavioral evidence showing the interference of absolute number in the proportional task, the multi-task model no longer works when asked to provide the number of target objects in the scene.

Ravi Shekhar, Sandro Pezzelle, Yauhen Klimovich et al.

In this paper, we aim to understand whether current language and vision (LaVi) models truly grasp the interaction between the two modalities. To this end, we propose an extension of the MSCOCO dataset, FOIL-COCO, which associates images with both correct and "foil" captions, that is, descriptions of the image that are highly similar to the original ones, but contain one single mistake ("foil word"). We show that current LaVi models fall into the traps of this data and perform badly on three tasks: a) caption classification (correct vs. foil); b) foil word detection; c) foil word correction. Humans, in contrast, have near-perfect performance on those tasks. We demonstrate that merely utilising language cues is not enough to model FOIL-COCO and that it challenges the state-of-the-art by requiring a fine-grained understanding of the relation between text and image.

Ionut Sorodoc, Sandro Pezzelle, Aurélie Herbelot et al.

Major advances have recently been made in merging language and vision representations. But most tasks considered so far have confined themselves to the processing of objects and lexicalised relations amongst objects (content words). We know, however, that humans (even pre-school children) can abstract over raw data to perform certain types of higher-level reasoning, expressed in natural language by function words. A case in point is given by their ability to learn quantifiers, i.e. expressions like 'few', 'some' and 'all'. From formal semantics and cognitive linguistics, we know that quantifiers are relations over sets which, as a simplification, we can see as proportions. For instance, in 'most fish are red', most encodes the proportion of fish which are red fish. In this paper, we study how well current language and vision strategies model such relations. We show that state-of-the-art attention mechanisms coupled with a traditional linguistic formalisation of quantifiers gives best performance on the task. Additionally, we provide insights on the role of 'gist' representations in quantification. A 'logical' strategy to tackle the task would be to first obtain a numerosity estimation for the two involved sets and then compare their cardinalities. We however argue that precisely identifying the composition of the sets is not only beyond current state-of-the-art models but perhaps even detrimental to a task that is most efficiently performed by refining the approximate numerosity estimator of the system.

Sandro Pezzelle, Marco Marelli, Raffaella Bernardi

People can refer to quantities in a visual scene by using either exact cardinals (e.g. one, two, three) or natural language quantifiers (e.g. few, most, all). In humans, these two processes underlie fairly different cognitive and neural mechanisms. Inspired by this evidence, the present study proposes two models for learning the objective meaning of cardinals and quantifiers from visual scenes containing multiple objects. We show that a model capitalizing on a 'fuzzy' measure of similarity is effective for learning quantifiers, whereas the learning of exact cardinals is better accomplished when information about number is provided.

Denis Paperno, Germán Kruszewski, Angeliki Lazaridou et al.

We introduce LAMBADA, a dataset to evaluate the capabilities of computational models for text understanding by means of a word prediction task. LAMBADA is a collection of narrative passages sharing the characteristic that human subjects are able to guess their last word if they are exposed to the whole passage, but not if they only see the last sentence preceding the target word. To succeed on LAMBADA, computational models cannot simply rely on local context, but must be able to keep track of information in the broader discourse. We show that LAMBADA exemplifies a wide range of linguistic phenomena, and that none of several state-of-the-art language models reaches accuracy above 1% on this novel benchmark. We thus propose LAMBADA as a challenging test set, meant to encourage the development of new models capable of genuine understanding of broad context in natural language text.